col.width <- c(37, 10, 1, 1, 3, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 8, 2, 2, 2, 4, 4, 1, 4, 1, 1,
1, 3, 2, 2, 8, 2, 5, 5, 5, 4, 5, 5, 5,4, 2, 1, 2, 1, 3, 1, 1, 1, 1, 1, 1, 3,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 6, 8,
8, 8, 2, 1, 1, 1, 1, 8, 1, 1, 8, 1, 1, 2, 2, 5, 2, 5, 3, 1, 3, 1, 8, 8, 2, 8,
2, 8, 2, 2, 1, 8, 1, 1, 1, 1, 1, 8, 1, 2, 2, 2, 2, 2, 1, 1, 1, 2, 1, 3, 1, 1,
1, 1, 1, 1, 1, 1, 1)
col.names.abr <- c("PUF_CASE_ID", "PUF_FACILITY_ID", "FACILITY_TYPE_CD", "FACILITY_LOCATION_CD",
"AGE", "SEX", "RACE", "SPANISH_HISPANIC_ORIGIN", "INSURANCE_STATUS",
"MED_INC_QUAR_00", "NO_HSD_QUAR_00", "UR_CD_03", "MED_INC_QUAR_12", "NO_HSD_QUAR_12",
"UR_CD_13", "CROWFLY", "CDCC_TOTAL_BEST", "SEQUENCE_NUMBER", "CLASS_OF_CASE",
"YEAR_OF_DIAGNOSIS", "PRIMARY_SITE", "LATERALITY", "HISTOLOGY", "BEHAVIOR", "GRADE",
"DIAGNOSTIC_CONFIRMATION", "TUMOR_SIZE", "REGIONAL_NODES_POSITIVE",
"REGIONAL_NODES_EXAMINED", "DX_STAGING_PROC_DAYS", "RX_SUMM_DXSTG_PROC", "TNM_CLIN_T",
"TNM_CLIN_N", "TNM_CLIN_M", "TNM_CLIN_STAGE_GROUP", "TNM_PATH_T", "TNM_PATH_N", "TNM_PATH_M",
"TNM_PATH_STAGE_GROUP", "TNM_EDITION_NUMBER", "ANALYTIC_STAGE_GROUP", "CS_METS_AT_DX",
"CS_METS_EVAL", "CS_EXTENSION", "CS_TUMOR_SIZEEXT_EVAL", "CS_METS_DX_BONE", "CS_METS_DX_BRAIN",
"CS_METS_DX_LIVER", "CS_METS_DX_LUNG", "LYMPH_VASCULAR_INVASION", "CS_SITESPECIFIC_FACTOR_1",
"CS_SITESPECIFIC_FACTOR_2", "CS_SITESPECIFIC_FACTOR_3", "CS_SITESPECIFIC_FACTOR_4",
"CS_SITESPECIFIC_FACTOR_5", "CS_SITESPECIFIC_FACTOR_6", "CS_SITESPECIFIC_FACTOR_7",
"CS_SITESPECIFIC_FACTOR_8", "CS_SITESPECIFIC_FACTOR_9", "CS_SITESPECIFIC_FACTOR_10",
"CS_SITESPECIFIC_FACTOR_11", "CS_SITESPECIFIC_FACTOR_12", "CS_SITESPECIFIC_FACTOR_13",
"CS_SITESPECIFIC_FACTOR_14", "CS_SITESPECIFIC_FACTOR_15", "CS_SITESPECIFIC_FACTOR_16",
"CS_SITESPECIFIC_FACTOR_17", "CS_SITESPECIFIC_FACTOR_18", "CS_SITESPECIFIC_FACTOR_19",
"CS_SITESPECIFIC_FACTOR_20", "CS_SITESPECIFIC_FACTOR_21", "CS_SITESPECIFIC_FACTOR_22",
"CS_SITESPECIFIC_FACTOR_23", "CS_SITESPECIFIC_FACTOR_24", "CS_SITESPECIFIC_FACTOR_25",
"CS_VERSION_LATEST", "DX_RX_STARTED_DAYS", "DX_SURG_STARTED_DAYS", "DX_DEFSURG_STARTED_DAYS",
"RX_SUMM_SURG_PRIM_SITE", "RX_HOSP_SURG_APPR_2010", "RX_SUMM_SURGICAL_MARGINS",
"RX_SUMM_SCOPE_REG_LN_SUR", "RX_SUMM_SURG_OTH_REGDIS", "SURG_DISCHARGE_DAYS", "READM_HOSP_30_DAYS",
"REASON_FOR_NO_SURGERY", "DX_RAD_STARTED_DAYS", "RX_SUMM_RADIATION", "RAD_LOCATION_OF_RX",
"RAD_TREAT_VOL", "RAD_REGIONAL_RX_MODALITY", "RAD_REGIONAL_DOSE_CGY", "RAD_BOOST_RX_MODALITY",
"RAD_BOOST_DOSE_CGY", "RAD_NUM_TREAT_VOL", "RX_SUMM_SURGRAD_SEQ", "RAD_ELAPSED_RX_DAYS",
"REASON_FOR_NO_RADIATION", "DX_SYSTEMIC_STARTED_DAYS", "DX_CHEMO_STARTED_DAYS", "RX_SUMM_CHEMO",
"DX_HORMONE_STARTED_DAYS", "RX_SUMM_HORMONE", "DX_IMMUNO_STARTED_DAYS", "RX_SUMM_IMMUNOTHERAPY",
"RX_SUMM_TRNSPLNT_ENDO", "RX_SUMM_SYSTEMIC_SUR_SEQ", "DX_OTHER_STARTED_DAYS", "RX_SUMM_OTHER",
"PALLIATIVE_CARE", "RX_SUMM_TREATMENT_STATUS", "PUF_30_DAY_MORT_CD", "PUF_90_DAY_MORT_CD",
"DX_LASTCONTACT_DEATH_MONTHS", "PUF_VITAL_STATUS", "RX_HOSP_SURG_PRIM_SITE", "RX_HOSP_CHEMO",
"RX_HOSP_IMMUNOTHERAPY", "RX_HOSP_HORMONE", "RX_HOSP_OTHER", "PUF_MULT_SOURCE", "REFERENCE_DATE_FLAG",
"RX_SUMM_SCOPE_REG_LN_2012", "RX_HOSP_DXSTG_PROC", "PALLIATIVE_CARE_HOSP", "TUMOR_SIZE_SUMMARY",
"METS_AT_DX_OTHER", "METS_AT_DX_DISTANT_LN", "METS_AT_DX_BONE", "METS_AT_DX_BRAIN",
"METS_AT_DX_LIVER", "METS_AT_DX_LUNG", "NO_HSD_QUAR_16", "MED_INC_QUAR_16", "MEDICAID_EXPN_CODE")
#Read in data for each subsite
lip <- read_fwf('NCDBPUF_Lip.3.2016.0.dat',
fwf_widths(col.width, col_names = col.names.abr),
col_types = cols(.default = col_character()))
melanoma <- read_fwf('NCDBPUF_Melanoma.3.2016.0.dat',
fwf_widths(col.width, col_names = col.names.abr),
col_types = cols(.default = col_character()))
skin <- read_fwf('NCDBPUF_OtSkin.3.2016.0.dat',
fwf_widths(col.width, col_names = col.names.abr),
col_types = cols(.default = col_character()))
hodgextr <- read_fwf('NCDBPUF_HodgExtr.3.2016.0.dat',
fwf_widths(col.width, col_names = col.names.abr),
col_types = cols(.default = col_character()))
hodgndal <- read_fwf('NCDBPUF_HodgNdal.3.2016.0.dat',
fwf_widths(col.width, col_names = col.names.abr),
col_types = cols(.default = col_character()))
NHLndal <- read_fwf('NCDBPUF_NHLNdal.3.2016.0.dat',
fwf_widths(col.width, col_names = col.names.abr),
col_types = cols(.default = col_character()))
#Combine data for all subsites
dat <- bind_rows(lip, melanoma, skin, hodgextr, hodgndal, NHLndal)
rm(lip, melanoma, skin, hodgextr, hodgndal, NHLndal)
#only works for melanoma
prim_site_text <- data_frame(PRIMARY_SITE = c("C440",
"C441",
"C442",
"C443",
"C444",
"C445",
"C446",
"C447",
"C448",
"C449",
"C510",
"C511",
"C512",
"C518",
"C519",
"C600",
"C601",
"C602",
"C608",
"C609",
"C632"),
SITE_TEXT = c(
"C44.0 Skin of lip, NOS",
"C44.1 Eyelid",
"C44.2 External ear",
"C44.3 Skin of ear and unspecified parts of face",
"C44.4 Skin of scalp and neck",
"C44.5 Skin of trunk",
"C44.6 Skin of upper limb and shoulder",
"C44.7 Skin of lower limb and hip",
"C44.8 Overlapping lesion of skin",
"C44.9 Skin, NOS",
"C51.0 Labium majus",
"C51.1 Labium minus",
"C51.2 Clitoris",
"C51.8 Overlapping lesion of vulva",
"C51.9 Vulva, NOS",
"C60.0 Prepuce",
"C60.1 Glans penis",
"C60.2 Body of penis",
"C60.8 Overlapping lesion of penis",
"C60.9 Penis",
"C63.2 Scrotum, NOS"))
dat <- merge(dat, prim_site_text, by = "PRIMARY_SITE", all.x = TRUE)
rm(prim_site_text)
# convert numeric variables from character class to numeric class
num_vars <- c("AGE", "CROWFLY", "TUMOR_SIZE", "DX_STAGING_PROC_DAYS", "DX_RX_STARTED_DAYS", "DX_SURG_STARTED_DAYS",
"DX_DEFSURG_STARTED_DAYS", "SURG_DISCHARGE_DAYS", "DX_RAD_STARTED_DAYS", "RAD_REGIONAL_DOSE_CGY",
"RAD_BOOST_DOSE_CGY", "RAD_ELAPSED_RX_DAYS", "DX_SYSTEMIC_STARTED_DAYS", "DX_CHEMO_STARTED_DAYS",
"DX_HORMONE_STARTED_DAYS", "DX_OTHER_STARTED_DAYS", "DX_LASTCONTACT_DEATH_MONTHS",
"RAD_NUM_TREAT_VOL")
dat[num_vars] <- lapply(dat[num_vars], as.numeric)
# convert factor variables from character class to factor class
vars <- names(dat)
fact_vars <- vars[!(vars %in% num_vars)] # basically all of the non-numerics
dat[fact_vars] <- lapply(dat[fact_vars], as.character)
dat[fact_vars] <- lapply(dat[fact_vars], as.factor)
dat <- dat %>%
mutate(FACILITY_TYPE_F = fct_recode(FACILITY_TYPE_CD,
"Community Cancer Program" = "1",
"Comprehensive Comm Ca Program" = "2",
"Academic/Research Program" = "3",
"Integrated Network Ca Program" = "4",
"Other" = "9")) %>%
mutate(FACILITY_LOCATION_F = fct_recode(FACILITY_LOCATION_CD,
"New England" = "1",
"Middle Atlantic" = "2",
"South Atlantic" = "3",
"East North Central" = "4",
"East South Central" = "5",
"West North Central" = "6",
"West South Central" = "7",
"Mountain" = "8",
"Pacific" = "9",
"out of US" = "0")) %>%
mutate(FACILITY_GEOGRAPHY = fct_collapse(FACILITY_LOCATION_CD,
"Northeast" = c("1", "2"),
"South" = c("3", "7"),
"Midwest" = c("4", "5", "6"),
"West" = c("8", "9"))) %>%
mutate(AGE_F = cut(AGE, c(0, 54, 64, 74, 100))) %>%
mutate(AGE_40 = cut(AGE, c(0, 40, 100))) %>%
mutate(SEX_F = fct_recode(SEX,
"Male" = "1",
"Female" = "2")) %>%
mutate(RACE_F = fct_collapse(RACE,
"White" = c("01"),
"Black" = c("02"),
"Asian" = c("04", "05", "06", "07", "08", "10", "11", "12", "13", "14", "15",
"16", "17", "20", "21", "22", "25", "26", "27", "28", "30", "31",
"32", "96", "97"),
"Other/Unk" = c("03", "98", "99"))) %>%
mutate(HISPANIC = fct_collapse(SPANISH_HISPANIC_ORIGIN,
"Yes" = c("1", "2", "3", "4", "5", "6", "7", "8"),
"No" = c("0"),
"Unknown" = c("9"))) %>%
mutate(INSURANCE_F = fct_recode(INSURANCE_STATUS,
"None" = "0",
"Private" = "1",
"Medicaid" = "2",
"Medicare" = "3",
"Other Government" = "4",
"Unknown" = "9")) %>%
mutate(INSURANCE_F = fct_relevel(INSURANCE_F,
"Private")) %>%
mutate(INCOME_F = fct_recode(MED_INC_QUAR_12,
"Less than $38,000" = "1",
"$38,000 - $47,999" = "2",
"$48,000 - $62,999" = "3",
"$63,000 +" = "4")) %>%
mutate(EDUCATION_F = fct_recode(NO_HSD_QUAR_12,
"21% or more" = "1",
"13 - 20.9%" = "2",
"7 - 12.9%" = "3",
"Less than 7%" = "4")) %>%
mutate(U_R_F = fct_collapse(UR_CD_13,
"Metro" = c("1", "2", "3"),
"Urban" = c("4", "5", "6", "7"),
"Rural" = c("8", "9"))) %>%
mutate(CLASS_OF_CASE_F = fct_collapse(CLASS_OF_CASE,
All_Part_Prim = c("10", "11", "12", "13",
"14", "20", "21", "22"),
Other_Facility = c("00"))) %>%
mutate(GRADE_F = fct_recode(GRADE,
"Gr I: Well Diff" = "1",
"Gr II: Mod Diff" = "2",
"Gr III: Poor Diff" = "3",
"Gr IV: Undiff/Anaplastic" = "4",
"NA/Unkown" = "9")) %>%
mutate(HISTOLOGY_F = fct_infreq(HISTOLOGY)) %>%
mutate(HISTOLOGY_F = factor(HISTOLOGY_F)) %>%
mutate(HISTOLOGY_F_LIM = fct_lump(HISTOLOGY_F, prop = 0.05)) %>%
mutate(TNM_CLIN_T = fct_recode(TNM_CLIN_T,
"N_A" = "88")) %>%
mutate(TNM_CLIN_T = fct_relevel(TNM_CLIN_T,
"1")) %>%
mutate(TNM_CLIN_N = fct_recode(TNM_CLIN_N,
"N_A" = "88")) %>%
mutate(TNM_CLIN_M = fct_recode(TNM_CLIN_M,
"N_A" = "88")) %>%
mutate(TNM_PATH_T = fct_recode(TNM_PATH_T,
"N_A" = "88")) %>%
mutate(TNM_PATH_T = fct_relevel(TNM_PATH_T,
"1")) %>%
mutate(TNM_PATH_N = fct_recode(TNM_PATH_N,
"N_A" = "88")) %>%
mutate(TNM_PATH_M = fct_recode(TNM_PATH_M,
"N_A" = "88")) %>%
mutate(TNM_CLIN_STAGE_GROUP = fct_recode(TNM_CLIN_STAGE_GROUP,
"N_A" = "88")) %>%
mutate(TNM_PATH_STAGE_GROUP = fct_recode(TNM_PATH_STAGE_GROUP,
"N_A" = "88")) %>%
mutate(MARGINS = fct_recode(RX_SUMM_SURGICAL_MARGINS,
"No Residual" = "0",
"Residual, NOS" = "1",
"Microscopic Resid" = "2",
"Macroscopic Resid" = "3",
"Not evaluable" = "7",
"No surg" = "8",
"Unknown" = "9")) %>%
mutate(MARGINS_YN = fct_collapse(RX_SUMM_SURGICAL_MARGINS,
"Yes" = c("1", "2", "3"),
"No" = c("0"),
"No surg/Unk/NA" = c("7", "8", "9"))) %>%
mutate(READM_HOSP_30_DAYS_F = fct_recode(READM_HOSP_30_DAYS,
"No_Surg_or_No_Readmit" = "0",
"Unplan_Readmit_Same" = "1",
"Plan_Readmit_Same" = "2",
"PlanUnplan_Same" = "3",
"Unknown" = "4")) %>%
mutate(RX_SUMM_RADIATION_F = fct_recode(RX_SUMM_RADIATION,
"None" = "0",
"Beam Radiation" = "1",
"Radioactive Implants" = "2",
"Radioisotopes" = "3",
"Beam + Imp or Isotopes" = "4",
"Radiation, NOS" = "5",
"Unknown" = "9")) %>%
mutate(PUF_30_DAY_MORT_CD_F = fct_recode(PUF_30_DAY_MORT_CD,
"Alive_30" = "0",
"Dead_30" = "1",
"Unknown" = "9")) %>%
mutate(PUF_90_DAY_MORT_CD_F = fct_recode(PUF_90_DAY_MORT_CD,
"Alive_90" = "0",
"Dead_90" = "1",
"Unknown" = "9")) %>%
mutate(LYMPH_VASCULAR_INVASION_F = fct_recode(LYMPH_VASCULAR_INVASION,
"Neg_LymphVasc_Inv" = "0",
"Pos_LumphVasc_Inv" = "1",
"N_A" = "8",
"Unknown" = "9")) %>%
mutate(RX_HOSP_SURG_APPR_2010_F = fct_recode(RX_HOSP_SURG_APPR_2010,
"No_Surg" = "0",
"Robot_Assist" = "1",
"Robot_to_Open" = "2",
"Endo_Lap" = "3",
"Endo_Lap_to_Open" = "4",
"Open_Unknown" = "5",
"Unknown" = "9")) %>%
mutate(All = "All") %>%
mutate(All = factor(All)) %>%
mutate(REASON_FOR_NO_SURGERY_F = fct_recode(REASON_FOR_NO_SURGERY,
"Surg performed" = "0",
"Surg not recommended" = "1",
"No surg due to pt factors" = "2",
"No surg, pt died" = "5",
"Surg rec, not done" = "6",
"Surg rec, pt refused" = "7",
"Surg rec, unk if done" = "8",
"Unknown" = "9")) %>%
mutate(SURGERY_YN = ifelse(REASON_FOR_NO_SURGERY == "0",
"Yes",
ifelse(REASON_FOR_NO_SURGERY == "9",
"Ukn",
"No"))) %>%
mutate(SURG_TF = case_when(SURGERY_YN == "Yes" ~ TRUE,
SURGERY_YN == "No" ~ FALSE,
TRUE ~ NA)) %>%
mutate(REASON_FOR_NO_RADIATION_F = fct_recode(REASON_FOR_NO_RADIATION,
"Rad performed" = "0",
"Rad not recommended" = "1",
"No Rad due to pt factors" = "2",
"No Rad, pt died" = "5",
"Rad rec, not done" = "6",
"Rad rec, pt refused" = "7",
"Rad rec, unk if done" = "8",
"Unknown" = "9")) %>%
mutate(RADIATION_YN = ifelse(REASON_FOR_NO_RADIATION == "0",
"Yes",
ifelse(REASON_FOR_NO_RADIATION == "9",
NA,
"No"))) %>%
mutate(SURGRAD_SEQ_F = fct_recode(RX_SUMM_SURGRAD_SEQ,
"None or Surg or Rad" = "0",
"Rad before Surg" = "2",
"Surg before Rad" = "3",
"Rad before and after Surg" = "4",
"Intraop Rad" = "5",
"Intraop Rad plus other" = "6",
"Unknown" = "9")) %>%
mutate(SURG_RAD_SEQ = ifelse(SURGERY_YN == "Yes" & RX_SUMM_SURGRAD_SEQ == "0",
"Surg Alone",
ifelse(RADIATION_YN == "Yes" & RX_SUMM_SURGRAD_SEQ == "0",
"Rad Alone",
ifelse(SURGERY_YN == "No" & RADIATION_YN == "No" & RX_SUMM_SURGRAD_SEQ == "0",
"No Treatment",
ifelse(RX_SUMM_SURGRAD_SEQ == "2",
"Rad then Surg",
ifelse(RX_SUMM_SURGRAD_SEQ == "3",
"Surg then Rad",
ifelse(RX_SUMM_SURGRAD_SEQ == "4",
"Rad before and after Surg",
"Other"))))))) %>%
mutate(SURG_RAD_SEQ = fct_relevel(SURG_RAD_SEQ,
"Surg Alone",
"Surg then Rad",
"Rad Alone")) %>%
mutate(CHEMO_YN = fct_collapse(RX_SUMM_CHEMO,
"No" = c("00", "82", "85", "86", "87"),
"Yes" = c("01", "02", "03"),
"Ukn" = c("88", "99"))) %>%
mutate(SURG_RAD_SEQ_C = ifelse(SURGERY_YN == "Yes" & RX_SUMM_SURGRAD_SEQ == "0" & CHEMO_YN == "No",
"Surg, No rad, No Chemo",
ifelse(RADIATION_YN == "Yes" & RX_SUMM_SURGRAD_SEQ == "0" & CHEMO_YN == "No",
"Rad, No Surg, No Chemo",
ifelse(SURGERY_YN == "No" & RADIATION_YN == "No" & RX_SUMM_SURGRAD_SEQ == "0" & CHEMO_YN == "No",
"No Surg, No Rad, No Chemo",
ifelse(RX_SUMM_SURGRAD_SEQ == "2" & CHEMO_YN == "No",
"Rad then Surg, No Chemo",
ifelse(RX_SUMM_SURGRAD_SEQ == "3" & CHEMO_YN == "No",
"Surg then Rad, No Chemo",
ifelse(RX_SUMM_SURGRAD_SEQ == "4" & CHEMO_YN == "No",
"Rad before and after Surg, No Chemo",
ifelse(SURGERY_YN == "Yes" & RX_SUMM_SURGRAD_SEQ == "0" & CHEMO_YN == "Yes",
"Surg, No rad, Yes Chemo",
ifelse(RADIATION_YN == "Yes" & RX_SUMM_SURGRAD_SEQ == "0" & CHEMO_YN == "Yes",
"Rad, No Surg, Yes Chemo",
ifelse(SURGERY_YN == "No" & RADIATION_YN == "No" & RX_SUMM_SURGRAD_SEQ == "0" & CHEMO_YN == "Yes",
"No Surg, No Rad, Yes Chemo",
ifelse(RX_SUMM_SURGRAD_SEQ == "2" & CHEMO_YN == "Yes",
"Rad then Surg, Yes Chemo",
ifelse(RX_SUMM_SURGRAD_SEQ == "3" & CHEMO_YN == "Yes",
"Surg then Rad, Yes Chemo",
ifelse(RX_SUMM_SURGRAD_SEQ == "4" & CHEMO_YN == "Yes",
"Rad before and after Surg, Yes Chemo",
"Other"))))))))))))) %>%
mutate(SURG_RAD_SEQ_C = fct_infreq(SURG_RAD_SEQ_C)) %>%
mutate(T_SIZE = as.numeric(TUMOR_SIZE)) %>%
mutate(T_SIZE = ifelse(T_SIZE == 0,
"No Tumor",
ifelse(T_SIZE > 0 & T_SIZE < 10 | T_SIZE == 991,
"< 1 cm",
ifelse(T_SIZE >= 10 & T_SIZE < 20 | T_SIZE == 992,
"1-2 cm",
ifelse(T_SIZE >= 20 & T_SIZE < 30 | T_SIZE == 993,
"2-3 cm",
ifelse(T_SIZE >= 30 & T_SIZE < 40 | T_SIZE == 994,
"3-4 cm",
ifelse(T_SIZE >= 40 & T_SIZE < 50 | T_SIZE == 995,
"4-5 cm",
ifelse(T_SIZE >= 50 & T_SIZE < 60 | T_SIZE == 996,
"5-6 cm",
ifelse(T_SIZE >= 60 & T_SIZE <= 987 |
T_SIZE == 980 | T_SIZE == 989 |
T_SIZE == 997,
">6 cm",
ifelse(T_SIZE == 988 | T_SIZE == 999,
"NA_unk",
"Microscopic focus")))))))))) %>%
mutate(T_SIZE = factor(T_SIZE)) %>%
mutate(T_SIZE = fct_relevel(T_SIZE,
"No Tumor", "Microscopic focus", "< 1 cm", "1-2 cm", "2-3 cm", "3-4 cm",
"4-5 cm", "5-6 cm", ">6 cm", "NA_unk")) %>%
mutate(mets_at_dx = case_when(CS_METS_DX_LUNG == "1" ~ "Lung",
CS_METS_DX_BONE == "1" ~ "Bone",
CS_METS_DX_BRAIN == "1" ~ "Brain",
CS_METS_DX_LIVER == "1" ~ "Liver",
TRUE ~ "None/Other/Unk/NA")) %>%
mutate(MEDICAID_EXPN_CODE = fct_recode(MEDICAID_EXPN_CODE,
"Non-Expansion State" = "0",
"Jan 2014 Expansion States" = "1",
"Early Expansion States (2010-13)" = "2",
"Late Expansion States (> Jan 2014)" = "3",
"Suppressed for Ages 0 - 39" = "9")) %>%
mutate(EXPN_GROUP = case_when(MEDICAID_EXPN_CODE %in% c("Jan 2014 Expansion States") &
YEAR_OF_DIAGNOSIS %in% c("2014", "2015") ~ "Post-Expansion",
MEDICAID_EXPN_CODE %in% c("Jan 2014 Expansion States") &
YEAR_OF_DIAGNOSIS %in%
c("2004", "2005", "2006", "2007", "2008",
"2009", "2010", "2011", "2012", "2013") ~ "Pre-Expansion",
MEDICAID_EXPN_CODE %in% c("Early Expansion States (2010-13)") &
YEAR_OF_DIAGNOSIS %in% c("2010", "2011", "2012", "2013", "2014", "2015") ~ "Post-Expansion",
MEDICAID_EXPN_CODE %in% c("Early Expansion States (2010-13)") &
YEAR_OF_DIAGNOSIS %in% c("2004", "2005", "2006", "2007", "2008", "2009") ~ "Pre-Expansion",
MEDICAID_EXPN_CODE %in% c("Non-Expansion State") ~ "Pre-Expansion",
MEDICAID_EXPN_CODE %in% c("Late Expansion States (> Jan 2014)") ~ "Pre-Expansion",
MEDICAID_EXPN_CODE %in% c("Late Expansion States (> Jan 2014)") &
YEAR_OF_DIAGNOSIS %in% c("2014", "2015") ~ "Exclude",
MEDICAID_EXPN_CODE == "Suppressed for Ages 0 - 39" ~ "Exclude")) %>%
mutate(pre_2014 = YEAR_OF_DIAGNOSIS %in% c("2004", "2005", "2006", "2007", "2008",
"2009", "2010", "2011", "2012", "2013")) %>%
mutate(mets_at_dx_F = ifelse(mets_at_dx == "None/Other/Unk/NA", FALSE, TRUE)) %>%
mutate(Tx_YN = ifelse(SURG_RAD_SEQ == "No Treatment" & CHEMO_YN == "No", FALSE,
ifelse(CHEMO_YN == "Ukn", NA,
TRUE)))
fact_vars_2 <- c("FACILITY_TYPE_F", "FACILITY_LOCATION_F", "AGE_F", "SEX_F", "RACE_F",
"HISPANIC", "INSURANCE_F", "INCOME_F", "EDUCATION_F", "U_R_F",
"CDCC_TOTAL_BEST", "CLASS_OF_CASE_F", "YEAR_OF_DIAGNOSIS", "PRIMARY_SITE", "HISTOLOGY",
"BEHAVIOR", "GRADE_F", "TNM_CLIN_T", "TNM_CLIN_N", "TNM_CLIN_M",
"TNM_CLIN_STAGE_GROUP", "TNM_PATH_T", "TNM_PATH_N", "TNM_PATH_M", "TNM_PATH_STAGE_GROUP",
"MARGINS", "READM_HOSP_30_DAYS_F", "RX_SUMM_RADIATION_F", "PUF_30_DAY_MORT_CD_F",
"PUF_90_DAY_MORT_CD_F", "LYMPH_VASCULAR_INVASION_F", "RX_HOSP_SURG_APPR_2010_F", "mets_at_dx")
dat <- dat %>%
mutate_at(fact_vars_2, funs(factor(.)))
functions
p_table <- function(tab_data, ...) {
tab_data_2 <- deparse(substitute(tab_data))
table_p <- do.call(CreateTableOne,
list(data = as.name(tab_data_2), includeNA = TRUE, ...))
table_p_out <- print(table_p,
showAllLevels = TRUE,
printToggle = FALSE)
kable(table_p_out,
align = "c")
}
uni_var <- function(test_var, data_imp) {
cat("_________________________________________________")
cat("\n")
cat(" \n##", test_var)
cat("\n")
cat("_________________________________________________")
cat("\n")
f <- as.formula(paste("Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS == 0)",
as.name(test_var),
sep = " ~ " ))
data_imp_2 <- deparse(substitute(data_imp))
km_fit <- do.call("survfit", list(formula = f, data = as.name(data_imp_2)))
print(km_fit)
cat("\n")
print(summary(km_fit, times = c(12, 24, 36, 48, 60, 120)))
cat("\n")
cat("\n")
cat("\n")
cat(" \n## Univariable Cox Proportional Hazard Model for: ", test_var)
cat("\n")
cat("\n")
n_levels <- nlevels(data_imp[[test_var]])
if(n_levels == 1){
print("Only one level, no Cox model performed")
cat("\n")
} else {
cox_fit <- do.call("coxph", list(formula = f, data = as.name(data_imp_2)))
print(summary(cox_fit))
cat("\n")
do.call("ggforest",
list(model = cox_fit, data = as.name(data_imp_2)))
}
cat("\n")
cat("\n")
cat("\n")
cat(" \n## Unadjusted Kaplan Meier Overall Survival Curve for: ", test_var)
p <- do.call("ggsurvplot",
list(fit = km_fit, data = as.name(data_imp_2),
palette = "jco", censor = FALSE, legend = "right",
linetype = "strata", xlab = "Time (Months)"))
print(p)
}
Kaplan Meier Analysis
All
uni_var(test_var = "All", data_imp = data)
## _________________________________________________
##
## ## All
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ All, data = data)
##
## n events median 0.95LCL 0.95UCL
## 362910 89972 164 162 165
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ All, data = data)
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 304157 21947 0.936 0.000417 0.935 0.937
## 24 261059 17623 0.880 0.000569 0.879 0.881
## 36 216079 13651 0.831 0.000675 0.829 0.832
## 48 178134 9949 0.790 0.000757 0.788 0.791
## 60 144302 7410 0.754 0.000828 0.752 0.756
## 120 34572 17189 0.613 0.001249 0.610 0.615
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: All
##
## [1] "Only one level, no Cox model performed"
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: All
Facility Type
uni_var(test_var = "FACILITY_TYPE_F", data_imp = data)
## _________________________________________________
##
## ## FACILITY_TYPE_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_TYPE_F, data = data)
##
## 41837 observations deleted due to missingness
## n events median 0.95LCL
## FACILITY_TYPE_F=Community Cancer Program 20025 6627 126 122
## FACILITY_TYPE_F=Comprehensive Comm Ca Program 114916 34156 144 142
## FACILITY_TYPE_F=Academic/Research Program 147602 35238 162 158
## FACILITY_TYPE_F=Integrated Network Ca Program 38530 10808 147 143
## 0.95UCL
## FACILITY_TYPE_F=Community Cancer Program 132
## FACILITY_TYPE_F=Comprehensive Comm Ca Program 146
## FACILITY_TYPE_F=Academic/Research Program NA
## FACILITY_TYPE_F=Integrated Network Ca Program 152
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_TYPE_F, data = data)
##
## 41837 observations deleted due to missingness
## FACILITY_TYPE_F=Community Cancer Program
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 16242 1969 0.897 0.00221 0.892 0.901
## 24 13658 1293 0.823 0.00283 0.817 0.828
## 36 11147 946 0.762 0.00323 0.756 0.768
## 48 9167 668 0.713 0.00354 0.707 0.720
## 60 7352 502 0.671 0.00380 0.664 0.679
## 120 1706 1106 0.515 0.00535 0.504 0.525
##
## FACILITY_TYPE_F=Comprehensive Comm Ca Program
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 95753 8748 0.920 0.000818 0.919 0.922
## 24 81903 6518 0.855 0.001087 0.853 0.857
## 36 67972 4953 0.800 0.001267 0.798 0.803
## 48 56271 3728 0.754 0.001406 0.751 0.756
## 60 46023 2747 0.714 0.001522 0.711 0.717
## 120 11044 6556 0.558 0.002195 0.553 0.562
##
## FACILITY_TYPE_F=Academic/Research Program
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 123953 7681 0.945 0.000613 0.944 0.946
## 24 105844 7140 0.888 0.000870 0.886 0.890
## 36 86436 5624 0.837 0.001051 0.835 0.839
## 48 70096 4059 0.795 0.001191 0.793 0.797
## 60 55804 3049 0.757 0.001317 0.755 0.760
## 120 12528 6853 0.606 0.002069 0.602 0.610
##
## FACILITY_TYPE_F=Integrated Network Ca Program
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 32077 2792 0.924 0.00139 0.921 0.927
## 24 27452 2016 0.863 0.00184 0.860 0.867
## 36 22620 1625 0.809 0.00216 0.805 0.813
## 48 18519 1144 0.765 0.00240 0.760 0.770
## 60 14948 840 0.727 0.00261 0.722 0.733
## 120 3461 2119 0.567 0.00391 0.559 0.575
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: FACILITY_TYPE_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_TYPE_F, data = data)
##
## n= 321073, number of events= 86829
## (41837 observations deleted due to missingness)
##
## coef exp(coef) se(coef)
## FACILITY_TYPE_FComprehensive Comm Ca Program -0.16443 0.84837 0.01342
## FACILITY_TYPE_FAcademic/Research Program -0.35814 0.69898 0.01339
## FACILITY_TYPE_FIntegrated Network Ca Program -0.20659 0.81336 0.01560
## z Pr(>|z|)
## FACILITY_TYPE_FComprehensive Comm Ca Program -12.25 <2e-16 ***
## FACILITY_TYPE_FAcademic/Research Program -26.75 <2e-16 ***
## FACILITY_TYPE_FIntegrated Network Ca Program -13.24 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef)
## FACILITY_TYPE_FComprehensive Comm Ca Program 0.8484 1.179
## FACILITY_TYPE_FAcademic/Research Program 0.6990 1.431
## FACILITY_TYPE_FIntegrated Network Ca Program 0.8134 1.229
## lower .95 upper .95
## FACILITY_TYPE_FComprehensive Comm Ca Program 0.8263 0.8710
## FACILITY_TYPE_FAcademic/Research Program 0.6809 0.7176
## FACILITY_TYPE_FIntegrated Network Ca Program 0.7889 0.8386
##
## Concordance= 0.535 (se = 0.001 )
## Rsquare= 0.003 (max possible= 0.999 )
## Likelihood ratio test= 1066 on 3 df, p=0
## Wald test = 1079 on 3 df, p=0
## Score (logrank) test = 1085 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: FACILITY_TYPE_F
Facility Location
uni_var(test_var = "FACILITY_LOCATION_F", data_imp = data)
## _________________________________________________
##
## ## FACILITY_LOCATION_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_LOCATION_F, data = data)
##
## 41837 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## FACILITY_LOCATION_F=New England 21270 5637 147 144 156
## FACILITY_LOCATION_F=Middle Atlantic 52367 13264 154 150 157
## FACILITY_LOCATION_F=South Atlantic 72796 20410 144 142 148
## FACILITY_LOCATION_F=East North Central 53630 14618 151 149 155
## FACILITY_LOCATION_F=East South Central 21009 6492 136 131 140
## FACILITY_LOCATION_F=West North Central 27272 6879 157 151 NA
## FACILITY_LOCATION_F=West South Central 16025 4815 146 139 153
## FACILITY_LOCATION_F=Mountain 17133 4508 153 148 161
## FACILITY_LOCATION_F=Pacific 39571 10206 NA NA NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_LOCATION_F, data = data)
##
## 41837 observations deleted due to missingness
## FACILITY_LOCATION_F=New England
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 17981 1277 0.937 0.00171 0.934 0.940
## 24 15509 1065 0.879 0.00235 0.875 0.884
## 36 12846 877 0.826 0.00281 0.821 0.832
## 48 10594 601 0.785 0.00313 0.779 0.791
## 60 8434 492 0.745 0.00345 0.739 0.752
## 120 1929 1149 0.581 0.00537 0.571 0.592
##
## FACILITY_LOCATION_F=Middle Atlantic
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 44645 3196 0.936 0.00110 0.934 0.938
## 24 37929 2675 0.877 0.00150 0.874 0.880
## 36 30808 2040 0.827 0.00179 0.823 0.830
## 48 24591 1549 0.781 0.00203 0.778 0.785
## 60 19240 1080 0.744 0.00223 0.739 0.748
## 120 3694 2426 0.586 0.00363 0.578 0.593
##
## FACILITY_LOCATION_F=South Atlantic
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 60080 4784 0.931 0.00097 0.929 0.932
## 24 51140 3921 0.867 0.00133 0.865 0.870
## 36 42412 3076 0.812 0.00158 0.809 0.815
## 48 34971 2301 0.765 0.00176 0.761 0.768
## 60 28464 1687 0.725 0.00192 0.721 0.729
## 120 6770 4105 0.564 0.00283 0.558 0.569
##
## FACILITY_LOCATION_F=East North Central
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 44891 3581 0.930 0.00113 0.928 0.932
## 24 38367 2827 0.869 0.00153 0.866 0.872
## 36 31453 2229 0.815 0.00181 0.811 0.819
## 48 25729 1592 0.771 0.00203 0.767 0.775
## 60 20748 1195 0.732 0.00222 0.728 0.736
## 120 4963 2833 0.577 0.00328 0.571 0.584
##
## FACILITY_LOCATION_F=East South Central
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 17689 1576 0.922 0.00190 0.918 0.925
## 24 14959 1312 0.851 0.00257 0.846 0.856
## 36 12339 969 0.792 0.00300 0.786 0.798
## 48 10142 722 0.743 0.00333 0.736 0.749
## 60 8140 527 0.701 0.00361 0.694 0.708
## 120 1873 1217 0.537 0.00528 0.526 0.547
##
## FACILITY_LOCATION_F=West North Central
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 22526 1684 0.934 0.00155 0.931 0.937
## 24 19360 1304 0.878 0.00210 0.874 0.882
## 36 15791 1092 0.825 0.00251 0.820 0.830
## 48 12855 751 0.783 0.00282 0.777 0.788
## 60 10288 580 0.744 0.00310 0.738 0.750
## 120 2307 1297 0.594 0.00476 0.585 0.603
##
## FACILITY_LOCATION_F=West South Central
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 13328 1417 0.908 0.00234 0.903 0.912
## 24 11177 962 0.839 0.00303 0.833 0.845
## 36 9198 685 0.784 0.00348 0.778 0.791
## 48 7559 501 0.739 0.00384 0.731 0.746
## 60 6099 389 0.698 0.00415 0.690 0.706
## 120 1195 781 0.552 0.00610 0.540 0.564
##
## FACILITY_LOCATION_F=Mountain
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 14210 1161 0.928 0.00202 0.925 0.932
## 24 12205 861 0.870 0.00271 0.865 0.875
## 36 10058 666 0.819 0.00318 0.813 0.826
## 48 8267 494 0.776 0.00356 0.769 0.783
## 60 6834 341 0.742 0.00386 0.734 0.749
## 120 1644 849 0.593 0.00586 0.582 0.605
##
## FACILITY_LOCATION_F=Pacific
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 32675 2514 0.933 0.00129 0.931 0.936
## 24 28211 2040 0.873 0.00177 0.869 0.876
## 36 23270 1514 0.822 0.00209 0.818 0.827
## 48 19345 1088 0.781 0.00233 0.777 0.786
## 60 15880 847 0.744 0.00254 0.740 0.749
## 120 4364 1977 0.606 0.00364 0.599 0.613
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: FACILITY_LOCATION_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_LOCATION_F, data = data)
##
## n= 321073, number of events= 86829
## (41837 observations deleted due to missingness)
##
## coef exp(coef) se(coef)
## FACILITY_LOCATION_FMiddle Atlantic -0.0018090 0.9981926 0.0159011
## FACILITY_LOCATION_FSouth Atlantic 0.0745691 1.0774198 0.0150466
## FACILITY_LOCATION_FEast North Central 0.0430144 1.0439529 0.0156783
## FACILITY_LOCATION_FEast South Central 0.1684812 1.1835059 0.0182054
## FACILITY_LOCATION_FWest North Central -0.0144924 0.9856121 0.0179659
## FACILITY_LOCATION_FWest South Central 0.1737202 1.1897227 0.0196242
## FACILITY_LOCATION_FMountain -0.0008789 0.9991215 0.0199809
## FACILITY_LOCATION_FPacific -0.0363362 0.9643160 0.0165960
## z Pr(>|z|)
## FACILITY_LOCATION_FMiddle Atlantic -0.114 0.90942
## FACILITY_LOCATION_FSouth Atlantic 4.956 7.2e-07 ***
## FACILITY_LOCATION_FEast North Central 2.744 0.00608 **
## FACILITY_LOCATION_FEast South Central 9.254 < 2e-16 ***
## FACILITY_LOCATION_FWest North Central -0.807 0.41986
## FACILITY_LOCATION_FWest South Central 8.852 < 2e-16 ***
## FACILITY_LOCATION_FMountain -0.044 0.96492
## FACILITY_LOCATION_FPacific -2.189 0.02856 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95
## FACILITY_LOCATION_FMiddle Atlantic 0.9982 1.0018 0.9676
## FACILITY_LOCATION_FSouth Atlantic 1.0774 0.9281 1.0461
## FACILITY_LOCATION_FEast North Central 1.0440 0.9579 1.0124
## FACILITY_LOCATION_FEast South Central 1.1835 0.8449 1.1420
## FACILITY_LOCATION_FWest North Central 0.9856 1.0146 0.9515
## FACILITY_LOCATION_FWest South Central 1.1897 0.8405 1.1448
## FACILITY_LOCATION_FMountain 0.9991 1.0009 0.9608
## FACILITY_LOCATION_FPacific 0.9643 1.0370 0.9335
## upper .95
## FACILITY_LOCATION_FMiddle Atlantic 1.0298
## FACILITY_LOCATION_FSouth Atlantic 1.1097
## FACILITY_LOCATION_FEast North Central 1.0765
## FACILITY_LOCATION_FEast South Central 1.2265
## FACILITY_LOCATION_FWest North Central 1.0209
## FACILITY_LOCATION_FWest South Central 1.2364
## FACILITY_LOCATION_FMountain 1.0390
## FACILITY_LOCATION_FPacific 0.9962
##
## Concordance= 0.517 (se = 0.001 )
## Rsquare= 0.001 (max possible= 0.999 )
## Likelihood ratio test= 331.4 on 8 df, p=0
## Wald test = 337.3 on 8 df, p=0
## Score (logrank) test = 337.9 on 8 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: FACILITY_LOCATION_F
Facility Geography
uni_var(test_var = "FACILITY_GEOGRAPHY", data_imp = data)
## _________________________________________________
##
## ## FACILITY_GEOGRAPHY
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_GEOGRAPHY, data = data)
##
## 41837 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## FACILITY_GEOGRAPHY=Northeast 73637 18901 153 147 156
## FACILITY_GEOGRAPHY=South 88821 25225 144 142 148
## FACILITY_GEOGRAPHY=Midwest 101911 27989 149 146 151
## FACILITY_GEOGRAPHY=West 56704 14714 NA 161 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_GEOGRAPHY, data = data)
##
## 41837 observations deleted due to missingness
## FACILITY_GEOGRAPHY=Northeast
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 62626 4473 0.936 0.000923 0.934 0.938
## 24 53438 3740 0.878 0.001266 0.876 0.880
## 36 43654 2917 0.827 0.001508 0.824 0.830
## 48 35185 2150 0.783 0.001702 0.779 0.786
## 60 27674 1572 0.744 0.001875 0.741 0.748
## 120 5623 3575 0.584 0.003008 0.578 0.590
##
## FACILITY_GEOGRAPHY=South
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 73408 6201 0.926 0.000901 0.925 0.928
## 24 62317 4883 0.862 0.001222 0.860 0.864
## 36 51610 3761 0.807 0.001438 0.804 0.810
## 48 42530 2802 0.760 0.001604 0.757 0.763
## 60 34563 2076 0.720 0.001743 0.717 0.724
## 120 7965 4886 0.561 0.002568 0.556 0.566
##
## FACILITY_GEOGRAPHY=Midwest
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 85106 6841 0.929 0.000825 0.928 0.931
## 24 72686 5443 0.868 0.001118 0.865 0.870
## 36 59583 4290 0.813 0.001323 0.810 0.815
## 48 48726 3065 0.768 0.001478 0.765 0.771
## 60 39176 2302 0.729 0.001615 0.725 0.732
## 120 9143 5347 0.573 0.002409 0.568 0.578
##
## FACILITY_GEOGRAPHY=West
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 46885 3675 0.932 0.00109 0.930 0.934
## 24 40416 2901 0.872 0.00148 0.869 0.875
## 36 33328 2180 0.822 0.00175 0.818 0.825
## 48 27612 1582 0.780 0.00195 0.776 0.784
## 60 22714 1188 0.744 0.00212 0.740 0.748
## 120 6008 2826 0.602 0.00309 0.596 0.608
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: FACILITY_GEOGRAPHY
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ FACILITY_GEOGRAPHY, data = data)
##
## n= 321073, number of events= 86829
## (41837 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## FACILITY_GEOGRAPHYSouth 0.094031 1.098594 0.009622 9.772 < 2e-16
## FACILITY_GEOGRAPHYMidwest 0.057178 1.058844 0.009416 6.072 1.26e-09
## FACILITY_GEOGRAPHYWest -0.024315 0.975978 0.010999 -2.211 0.0271
##
## FACILITY_GEOGRAPHYSouth ***
## FACILITY_GEOGRAPHYMidwest ***
## FACILITY_GEOGRAPHYWest *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## FACILITY_GEOGRAPHYSouth 1.099 0.9103 1.0781 1.1195
## FACILITY_GEOGRAPHYMidwest 1.059 0.9444 1.0395 1.0786
## FACILITY_GEOGRAPHYWest 0.976 1.0246 0.9552 0.9972
##
## Concordance= 0.512 (se = 0.001 )
## Rsquare= 0.001 (max possible= 0.999 )
## Likelihood ratio test= 173.3 on 3 df, p=0
## Wald test = 172.8 on 3 df, p=0
## Score (logrank) test = 172.9 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: FACILITY_GEOGRAPHY
Age Group
uni_var(test_var = "AGE_F", data_imp = data)
## _________________________________________________
##
## ## AGE_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ AGE_F, data = data)
##
## 34 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## AGE_F=(0,54] 123853 13264 NA NA NA
## AGE_F=(54,64] 79330 13732 NA NA NA
## AGE_F=(64,74] 76938 20008 139.4 138.0 141.9
## AGE_F=(74,100] 82755 42964 59.7 59.1 60.4
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ AGE_F, data = data)
##
## 34 observations deleted due to missingness
## AGE_F=(0,54]
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 106374 3468 0.970 0.000498 0.969 0.971
## 24 94556 2739 0.944 0.000690 0.943 0.946
## 36 81723 2031 0.923 0.000823 0.921 0.924
## 48 70239 1454 0.905 0.000927 0.903 0.907
## 60 59008 1047 0.891 0.001015 0.889 0.893
## 120 16859 2249 0.839 0.001483 0.836 0.842
##
## AGE_F=(54,64]
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 66772 3653 0.951 0.000786 0.950 0.953
## 24 58185 2649 0.912 0.001064 0.910 0.914
## 36 48718 2102 0.877 0.001271 0.874 0.879
## 48 40530 1456 0.849 0.001429 0.846 0.851
## 60 33238 1023 0.825 0.001564 0.822 0.828
## 120 8217 2499 0.725 0.002443 0.721 0.730
##
## AGE_F=(64,74]
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 64339 4647 0.936 0.000904 0.935 0.938
## 24 55056 3600 0.882 0.001228 0.879 0.884
## 36 44903 2968 0.831 0.001472 0.828 0.834
## 48 36459 2189 0.787 0.001666 0.784 0.790
## 60 28999 1618 0.749 0.001837 0.745 0.752
## 120 6181 4296 0.565 0.003012 0.559 0.571
##
## AGE_F=(74,100]
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 66647 10178 0.872 0.00119 0.870 0.874
## 24 53243 8634 0.755 0.00156 0.752 0.758
## 36 40718 6549 0.656 0.00177 0.653 0.660
## 48 30892 4850 0.572 0.00191 0.569 0.576
## 60 23046 3721 0.498 0.00202 0.494 0.502
## 120 3310 8145 0.229 0.00247 0.225 0.234
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: AGE_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ AGE_F, data = data)
##
## n= 362876, number of events= 89968
## (34 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## AGE_F(54,64] 0.570757 1.769606 0.012178 46.87 <2e-16 ***
## AGE_F(64,74] 1.044519 2.842031 0.011211 93.17 <2e-16 ***
## AGE_F(74,100] 1.915597 6.790994 0.009999 191.59 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## AGE_F(54,64] 1.770 0.5651 1.728 1.812
## AGE_F(64,74] 2.842 0.3519 2.780 2.905
## AGE_F(74,100] 6.791 0.1473 6.659 6.925
##
## Concordance= 0.68 (se = 0.001 )
## Rsquare= 0.125 (max possible= 0.998 )
## Likelihood ratio test= 48267 on 3 df, p=0
## Wald test = 46114 on 3 df, p=0
## Score (logrank) test = 56187 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: AGE_F
Age Group
uni_var(test_var = "AGE_40", data_imp = data)
## _________________________________________________
##
## ## AGE_40
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ AGE_40, data = data)
##
## 34 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## AGE_40=(0,40] 45430 3484 NA NA NA
## AGE_40=(40,100] 317446 86484 150 149 152
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ AGE_40, data = data)
##
## 34 observations deleted due to missingness
## AGE_40=(0,40]
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 39270 846 0.980 0.000677 0.979 0.981
## 24 34993 735 0.961 0.000965 0.959 0.963
## 36 30341 544 0.945 0.001165 0.943 0.947
## 48 26165 400 0.932 0.001325 0.929 0.934
## 60 21941 292 0.921 0.001462 0.918 0.923
## 120 6350 612 0.881 0.002175 0.877 0.885
##
## AGE_40=(40,100]
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 264862 21100 0.930 0.000465 0.929 0.931
## 24 226047 16887 0.868 0.000632 0.867 0.870
## 36 185721 13106 0.815 0.000748 0.813 0.816
## 48 151955 9549 0.770 0.000836 0.768 0.771
## 60 122350 7117 0.731 0.000914 0.729 0.732
## 120 28217 16577 0.574 0.001372 0.572 0.577
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: AGE_40
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ AGE_40, data = data)
##
## n= 362876, number of events= 89968
## (34 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## AGE_40(40,100] 1.41156 4.10235 0.01729 81.66 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## AGE_40(40,100] 4.102 0.2438 3.966 4.244
##
## Concordance= 0.548 (se = 0.001 )
## Rsquare= 0.029 (max possible= 0.998 )
## Likelihood ratio test= 10562 on 1 df, p=0
## Wald test = 6669 on 1 df, p=0
## Score (logrank) test = 7851 on 1 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: AGE_40
Gender
uni_var(test_var = "SEX_F", data_imp = data)
## _________________________________________________
##
## ## SEX_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SEX_F, data = data)
##
## n events median 0.95LCL 0.95UCL
## SEX_F=Male 207765 60900 140 139 142
## SEX_F=Female 155145 29072 NA NA NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SEX_F, data = data)
##
## SEX_F=Male
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 172446 14990 0.924 0.000597 0.923 0.925
## 24 146109 12112 0.856 0.000810 0.855 0.858
## 36 119424 9256 0.799 0.000954 0.797 0.800
## 48 97169 6775 0.750 0.001063 0.748 0.752
## 60 77841 5036 0.708 0.001158 0.706 0.710
## 120 17787 11370 0.546 0.001703 0.542 0.549
##
## SEX_F=Female
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 131711 6957 0.953 0.000555 0.952 0.954
## 24 114950 5511 0.911 0.000763 0.910 0.913
## 36 96655 4395 0.874 0.000915 0.872 0.876
## 48 80965 3174 0.843 0.001033 0.841 0.845
## 60 66461 2374 0.816 0.001138 0.814 0.819
## 120 16785 5819 0.703 0.001777 0.700 0.707
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: SEX_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SEX_F, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## SEX_FFemale -0.527427 0.590122 0.007132 -73.95 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## SEX_FFemale 0.5901 1.695 0.5819 0.5984
##
## Concordance= 0.561 (se = 0.001 )
## Rsquare= 0.016 (max possible= 0.998 )
## Likelihood ratio test= 5762 on 1 df, p=0
## Wald test = 5469 on 1 df, p=0
## Score (logrank) test = 5597 on 1 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: SEX_F
RACE_F
uni_var(test_var = "RACE_F", data_imp = data)
## _________________________________________________
##
## ## RACE_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RACE_F, data = data)
##
## n events median 0.95LCL 0.95UCL
## RACE_F=White 353647 87552 164.4 161.8 165
## RACE_F=Black 2116 907 73.1 65.5 84
## RACE_F=Other/Unk 6088 1213 NA NA NA
## RACE_F=Asian 1059 300 NA 141.8 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RACE_F, data = data)
##
## RACE_F=White
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 296701 21227 0.937 0.000421 0.936 0.938
## 24 254717 17131 0.880 0.000575 0.879 0.882
## 36 210851 13290 0.831 0.000683 0.830 0.833
## 48 173829 9704 0.790 0.000766 0.789 0.792
## 60 140792 7222 0.755 0.000838 0.753 0.756
## 120 33608 16816 0.613 0.001267 0.610 0.615
##
## RACE_F=Black
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1583 341 0.831 0.00835 0.815 0.848
## 24 1291 170 0.739 0.00999 0.720 0.759
## 36 1016 125 0.663 0.01105 0.641 0.685
## 48 789 89 0.601 0.01182 0.578 0.624
## 60 601 68 0.545 0.01251 0.521 0.570
## 120 132 102 0.409 0.01570 0.379 0.441
##
## RACE_F=Other/Unk
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5045 278 0.951 0.00288 0.945 0.956
## 24 4376 251 0.901 0.00409 0.893 0.909
## 36 3680 188 0.860 0.00489 0.850 0.870
## 48 3110 123 0.829 0.00545 0.819 0.840
## 60 2594 103 0.800 0.00598 0.788 0.812
## 120 749 245 0.689 0.00864 0.672 0.706
##
## RACE_F=Asian
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 828 101 0.898 0.00962 0.880 0.917
## 24 675 71 0.817 0.01270 0.793 0.842
## 36 532 48 0.754 0.01465 0.726 0.783
## 48 406 33 0.702 0.01620 0.671 0.734
## 60 315 17 0.670 0.01723 0.637 0.704
## 120 83 26 0.585 0.02227 0.543 0.630
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: RACE_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RACE_F, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## RACE_FBlack 0.75331 2.12402 0.03338 22.569 < 2e-16 ***
## RACE_FOther/Unk -0.25173 0.77745 0.02891 -8.707 < 2e-16 ***
## RACE_FAsian 0.28409 1.32855 0.05783 4.912 9.01e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## RACE_FBlack 2.1240 0.4708 1.9895 2.2676
## RACE_FOther/Unk 0.7775 1.2862 0.7346 0.8228
## RACE_FAsian 1.3285 0.7527 1.1862 1.4880
##
## Concordance= 0.505 (se = 0 )
## Rsquare= 0.001 (max possible= 0.998 )
## Likelihood ratio test= 511.8 on 3 df, p=0
## Wald test = 613.3 on 3 df, p=0
## Score (logrank) test = 639 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: RACE_F
Hispanic
uni_var(test_var = "HISPANIC", data_imp = data)
## _________________________________________________
##
## ## HISPANIC
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ HISPANIC, data = data)
##
## n events median 0.95LCL 0.95UCL
## HISPANIC=No 338276 83282 163 162 165
## HISPANIC=Yes 5052 1341 NA 145 NA
## HISPANIC=Unknown 19582 5349 NA NA NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ HISPANIC, data = data)
##
## HISPANIC=No
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 283450 20334 0.937 0.000431 0.936 0.937
## 24 242887 16388 0.880 0.000589 0.879 0.881
## 36 200359 12724 0.831 0.000700 0.830 0.832
## 48 164465 9264 0.790 0.000786 0.788 0.791
## 60 132607 6841 0.754 0.000861 0.752 0.756
## 120 31127 15746 0.612 0.001309 0.609 0.614
##
## HISPANIC=Yes
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4050 420 0.912 0.00413 0.903 0.920
## 24 3338 303 0.840 0.00549 0.829 0.851
## 36 2681 199 0.786 0.00634 0.773 0.798
## 48 2162 134 0.743 0.00698 0.730 0.757
## 60 1709 90 0.709 0.00753 0.695 0.724
## 120 362 174 0.595 0.01064 0.575 0.616
##
## HISPANIC=Unknown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 16657 1193 0.936 0.00179 0.933 0.940
## 24 14834 932 0.882 0.00241 0.878 0.887
## 36 13039 728 0.837 0.00280 0.832 0.843
## 48 11507 551 0.800 0.00309 0.794 0.806
## 60 9986 479 0.765 0.00334 0.759 0.772
## 120 3083 1269 0.629 0.00458 0.620 0.638
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: HISPANIC
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ HISPANIC, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## HISPANICYes 0.17257 1.18835 0.02753 6.269 3.64e-10 ***
## HISPANICUnknown -0.05147 0.94983 0.01412 -3.646 0.000266 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## HISPANICYes 1.1883 0.8415 1.1259 1.2542
## HISPANICUnknown 0.9498 1.0528 0.9239 0.9765
##
## Concordance= 0.503 (se = 0 )
## Rsquare= 0 (max possible= 0.998 )
## Likelihood ratio test= 52.05 on 2 df, p=4.972e-12
## Wald test = 54.04 on 2 df, p=1.84e-12
## Score (logrank) test = 54.15 on 2 df, p=1.741e-12
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: HISPANIC
Insurance Status
uni_var(test_var = "INSURANCE_F", data_imp = data)
## _________________________________________________
##
## ## INSURANCE_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ INSURANCE_F, data = data)
##
## n events median 0.95LCL 0.95UCL
## INSURANCE_F=Private 196431 26154 NA NA NA
## INSURANCE_F=None 8903 2462 165.2 165 NA
## INSURANCE_F=Medicaid 9359 2921 139.3 127 150.7
## INSURANCE_F=Medicare 144437 57598 86.8 86 87.6
## INSURANCE_F=Other Government 3780 837 160.3 160 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ INSURANCE_F, data = data)
##
## INSURANCE_F=Private
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 168550 5841 0.968 0.000407 0.968 0.969
## 24 149287 5097 0.938 0.000577 0.937 0.939
## 36 127672 4149 0.910 0.000703 0.909 0.912
## 48 108390 2942 0.888 0.000798 0.886 0.889
## 60 90243 2240 0.868 0.000883 0.866 0.870
## 120 24426 5180 0.790 0.001370 0.787 0.792
##
## INSURANCE_F=None
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7020 885 0.895 0.00335 0.888 0.901
## 24 5936 498 0.829 0.00422 0.820 0.837
## 36 4958 357 0.776 0.00478 0.767 0.786
## 48 4101 250 0.735 0.00520 0.724 0.745
## 60 3264 141 0.707 0.00550 0.696 0.718
## 120 777 302 0.604 0.00757 0.589 0.619
##
## INSURANCE_F=Medicaid
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7089 1207 0.863 0.00366 0.856 0.871
## 24 5580 624 0.783 0.00452 0.774 0.792
## 36 4214 372 0.726 0.00508 0.716 0.736
## 48 3298 240 0.680 0.00555 0.669 0.691
## 60 2551 145 0.647 0.00592 0.636 0.659
## 120 552 301 0.528 0.00837 0.512 0.544
##
## INSURANCE_F=Medicare
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 118458 13738 0.901 0.000806 0.899 0.902
## 24 97750 11209 0.812 0.001077 0.810 0.814
## 36 77222 8653 0.735 0.001253 0.733 0.738
## 48 60748 6438 0.669 0.001385 0.667 0.672
## 60 46997 4839 0.611 0.001496 0.608 0.614
## 120 8575 11291 0.379 0.002129 0.375 0.383
##
## INSURANCE_F=Other Government
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3040 276 0.922 0.00453 0.913 0.931
## 24 2506 195 0.859 0.00605 0.847 0.871
## 36 2013 120 0.815 0.00698 0.801 0.828
## 48 1597 79 0.780 0.00771 0.765 0.795
## 60 1247 45 0.755 0.00828 0.739 0.772
## 120 242 115 0.637 0.01336 0.611 0.663
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: INSURANCE_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ INSURANCE_F, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## INSURANCE_FNone 0.897310 2.452997 0.021084 42.56 <2e-16
## INSURANCE_FMedicaid 1.179156 3.251627 0.019523 60.40 <2e-16
## INSURANCE_FMedicare 1.313677 3.719828 0.007489 175.40 <2e-16
## INSURANCE_FOther Government 0.727012 2.068889 0.035119 20.70 <2e-16
## INSURANCE_FUnknown NA NA 0.000000 NA NA
##
## INSURANCE_FNone ***
## INSURANCE_FMedicaid ***
## INSURANCE_FMedicare ***
## INSURANCE_FOther Government ***
## INSURANCE_FUnknown
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## INSURANCE_FNone 2.453 0.4077 2.354 2.556
## INSURANCE_FMedicaid 3.252 0.3075 3.130 3.378
## INSURANCE_FMedicare 3.720 0.2688 3.666 3.775
## INSURANCE_FOther Government 2.069 0.4834 1.931 2.216
## INSURANCE_FUnknown NA NA NA NA
##
## Concordance= 0.647 (se = 0.001 )
## Rsquare= 0.091 (max possible= 0.998 )
## Likelihood ratio test= 34566 on 4 df, p=0
## Wald test = 31004 on 4 df, p=0
## Score (logrank) test = 35429 on 4 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: INSURANCE_F
Overall Survival pre/post-ACA expansion
uni_var(test_var = "EXPN_GROUP", data_imp = no_Excludes)
## _________________________________________________
##
## ## EXPN_GROUP
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ EXPN_GROUP, data = no_Excludes)
##
## n events median 0.95LCL 0.95UCL
## EXPN_GROUP=Post-Expansion 57862 10046 NA NA NA
## EXPN_GROUP=Pre-Expansion 278211 84641 147 146 149
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ EXPN_GROUP, data = no_Excludes)
##
## EXPN_GROUP=Post-Expansion
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 45462 3817 0.929 0.00111 0.927 0.931
## 24 33837 2728 0.868 0.00154 0.865 0.871
## 36 20120 1681 0.815 0.00192 0.811 0.818
## 48 11866 896 0.769 0.00236 0.764 0.773
## 60 7412 497 0.729 0.00283 0.724 0.735
##
## EXPN_GROUP=Pre-Expansion
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 233209 20815 0.922 0.000522 0.921 0.923
## 24 202961 16126 0.856 0.000695 0.855 0.857
## 36 174188 12427 0.801 0.000806 0.800 0.803
## 48 147051 9219 0.757 0.000885 0.755 0.758
## 60 120495 6991 0.718 0.000953 0.716 0.720
## 120 29573 16837 0.566 0.001353 0.563 0.568
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: EXPN_GROUP
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ EXPN_GROUP, data = no_Excludes)
##
## n= 336073, number of events= 94687
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EXPN_GROUPPre-Expansion 0.06250 1.06449 0.01072 5.828 5.61e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## EXPN_GROUPPre-Expansion 1.064 0.9394 1.042 1.087
##
## Concordance= 0.504 (se = 0.001 )
## Rsquare= 0 (max possible= 0.999 )
## Likelihood ratio test= 34.49 on 1 df, p=4.286e-09
## Wald test = 33.97 on 1 df, p=5.607e-09
## Score (logrank) test = 33.98 on 1 df, p=5.576e-09
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: EXPN_GROUP
Education
uni_var(test_var = "EDUCATION_F", data_imp = data)
## _________________________________________________
##
## ## EDUCATION_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ EDUCATION_F, data = data)
##
## 1490 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## EDUCATION_F=21% or more 36157 11317 139 134 142
## EDUCATION_F=13 - 20.9% 77301 21594 151 147 154
## EDUCATION_F=7 - 12.9% 126598 31601 162 161 NA
## EDUCATION_F=Less than 7% 121364 25137 NA NA NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ EDUCATION_F, data = data)
##
## 1490 observations deleted due to missingness
## EDUCATION_F=21% or more
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 29746 3036 0.912 0.00153 0.909 0.915
## 24 25060 2349 0.837 0.00204 0.833 0.841
## 36 20505 1695 0.777 0.00236 0.772 0.782
## 48 16928 1209 0.728 0.00260 0.723 0.733
## 60 13674 884 0.687 0.00279 0.682 0.693
## 120 3213 1892 0.540 0.00392 0.533 0.548
##
## EDUCATION_F=13 - 20.9%
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 64315 5467 0.926 0.000969 0.924 0.927
## 24 54669 4263 0.862 0.001306 0.859 0.864
## 36 44993 3213 0.808 0.001533 0.805 0.811
## 48 36957 2354 0.763 0.001708 0.759 0.766
## 60 29767 1743 0.724 0.001859 0.720 0.727
## 120 7011 4059 0.570 0.002748 0.564 0.575
##
## EDUCATION_F=7 - 12.9%
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 106148 7706 0.936 0.000708 0.934 0.937
## 24 90972 6119 0.880 0.000964 0.878 0.881
## 36 74962 4856 0.829 0.001148 0.827 0.832
## 48 61570 3532 0.787 0.001289 0.785 0.790
## 60 49939 2620 0.751 0.001412 0.748 0.754
## 120 12025 5994 0.609 0.002122 0.605 0.613
##
## EDUCATION_F=Less than 7%
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 102819 5667 0.951 0.000640 0.949 0.952
## 24 89468 4825 0.904 0.000893 0.902 0.906
## 36 74880 3837 0.863 0.001073 0.861 0.865
## 48 62086 2815 0.828 0.001215 0.826 0.830
## 60 50461 2131 0.797 0.001342 0.794 0.800
## 120 12233 5190 0.667 0.002110 0.663 0.671
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: EDUCATION_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ EDUCATION_F, data = data)
##
## n= 361420, number of events= 89649
## (1490 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## EDUCATION_F13 - 20.9% -0.13004 0.87806 0.01160 -11.21 <2e-16 ***
## EDUCATION_F7 - 12.9% -0.26039 0.77075 0.01095 -23.77 <2e-16 ***
## EDUCATION_FLess than 7% -0.47909 0.61935 0.01132 -42.32 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## EDUCATION_F13 - 20.9% 0.8781 1.139 0.8583 0.8983
## EDUCATION_F7 - 12.9% 0.7707 1.297 0.7544 0.7875
## EDUCATION_FLess than 7% 0.6193 1.615 0.6058 0.6332
##
## Concordance= 0.548 (se = 0.001 )
## Rsquare= 0.006 (max possible= 0.998 )
## Likelihood ratio test= 2342 on 3 df, p=0
## Wald test = 2335 on 3 df, p=0
## Score (logrank) test = 2360 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: EDUCATION_F
Urban/Rural
uni_var(test_var = "U_R_F", data_imp = data)
## _________________________________________________
##
## ## U_R_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ U_R_F, data = data)
##
## 11037 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## U_R_F=Metro 297888 72541 165 164 NA
## U_R_F=Urban 47786 12979 153 148 157
## U_R_F=Rural 6199 1825 141 134 149
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ U_R_F, data = data)
##
## 11037 observations deleted due to missingness
## U_R_F=Metro
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 249758 17698 0.937 0.000456 0.936 0.938
## 24 214853 14140 0.882 0.000623 0.881 0.883
## 36 178176 10974 0.834 0.000739 0.833 0.835
## 48 147112 8058 0.794 0.000830 0.792 0.795
## 60 119251 6004 0.759 0.000909 0.757 0.760
## 120 28714 13883 0.620 0.001369 0.617 0.623
##
## U_R_F=Urban
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 40132 3196 0.930 0.00120 0.927 0.932
## 24 34165 2546 0.868 0.00163 0.865 0.871
## 36 28024 1986 0.814 0.00192 0.811 0.818
## 48 22962 1412 0.770 0.00215 0.766 0.775
## 60 18526 1058 0.732 0.00234 0.727 0.737
## 120 4346 2477 0.576 0.00353 0.569 0.583
##
## U_R_F=Rural
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5179 439 0.926 0.00341 0.919 0.932
## 24 4360 378 0.855 0.00470 0.846 0.865
## 36 3585 277 0.798 0.00551 0.787 0.809
## 48 2881 216 0.746 0.00619 0.734 0.758
## 60 2314 141 0.706 0.00670 0.693 0.719
## 120 516 332 0.549 0.00986 0.530 0.568
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: U_R_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ U_R_F, data = data)
##
## n= 351873, number of events= 87345
## (11037 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## U_R_FUrban 0.128419 1.137029 0.009531 13.47 <2e-16 ***
## U_R_FRural 0.227046 1.254888 0.023701 9.58 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## U_R_FUrban 1.137 0.8795 1.116 1.158
## U_R_FRural 1.255 0.7969 1.198 1.315
##
## Concordance= 0.509 (se = 0.001 )
## Rsquare= 0.001 (max possible= 0.998 )
## Likelihood ratio test= 249 on 2 df, p=0
## Wald test = 258.5 on 2 df, p=0
## Score (logrank) test = 259.1 on 2 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: U_R_F
Year
uni_var(test_var = "YEAR_OF_DIAGNOSIS", data_imp = data)
## _________________________________________________
##
## ## YEAR_OF_DIAGNOSIS
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ YEAR_OF_DIAGNOSIS, data = data)
##
## n events median 0.95LCL 0.95UCL
## YEAR_OF_DIAGNOSIS=2004 23341 8432 NA 164.6 NA
## YEAR_OF_DIAGNOSIS=2005 25400 8688 157.6 154.8 NA
## YEAR_OF_DIAGNOSIS=2006 25979 8817 143.3 143.3 NA
## YEAR_OF_DIAGNOSIS=2007 27201 8757 NA 131.0 NA
## YEAR_OF_DIAGNOSIS=2008 28353 8878 NA NA NA
## YEAR_OF_DIAGNOSIS=2009 29626 8524 NA 107.1 NA
## YEAR_OF_DIAGNOSIS=2010 29968 8076 95.5 95.0 NA
## YEAR_OF_DIAGNOSIS=2011 31345 7787 NA 83.3 NA
## YEAR_OF_DIAGNOSIS=2012 32394 6814 71.8 71.7 NA
## YEAR_OF_DIAGNOSIS=2013 34625 6286 NA NA NA
## YEAR_OF_DIAGNOSIS=2014 36169 5073 NA NA NA
## YEAR_OF_DIAGNOSIS=2015 38509 3840 NA NA NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ YEAR_OF_DIAGNOSIS, data = data)
##
## YEAR_OF_DIAGNOSIS=2004
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 20534 1362 0.940 0.00159 0.937 0.943
## 24 18897 1200 0.884 0.00216 0.880 0.888
## 36 17618 1006 0.837 0.00251 0.832 0.841
## 48 16580 775 0.799 0.00273 0.794 0.805
## 60 15531 700 0.765 0.00290 0.760 0.771
## 120 9840 2468 0.631 0.00344 0.624 0.638
##
## YEAR_OF_DIAGNOSIS=2005
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 22550 1409 0.943 0.00148 0.940 0.946
## 24 20906 1253 0.890 0.00201 0.886 0.894
## 36 19614 1045 0.845 0.00234 0.841 0.850
## 48 18526 824 0.809 0.00255 0.804 0.814
## 60 17333 754 0.776 0.00272 0.771 0.781
## 120 10971 2625 0.646 0.00326 0.639 0.652
##
## YEAR_OF_DIAGNOSIS=2006
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 22924 1546 0.939 0.00151 0.936 0.942
## 24 21237 1277 0.886 0.00203 0.882 0.890
## 36 19737 1178 0.836 0.00237 0.832 0.841
## 48 18347 997 0.794 0.00261 0.788 0.799
## 60 17024 804 0.758 0.00277 0.753 0.764
## 120 9515 2621 0.626 0.00330 0.619 0.632
##
## YEAR_OF_DIAGNOSIS=2007
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 23826 1705 0.935 0.00152 0.932 0.938
## 24 21930 1425 0.879 0.00204 0.875 0.883
## 36 20397 1196 0.830 0.00236 0.826 0.835
## 48 19019 950 0.791 0.00256 0.786 0.796
## 60 17522 746 0.760 0.00271 0.754 0.765
## 120 4243 2625 0.621 0.00341 0.614 0.627
##
## YEAR_OF_DIAGNOSIS=2008
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 24610 1800 0.934 0.00150 0.931 0.937
## 24 22521 1550 0.875 0.00203 0.871 0.879
## 36 20830 1248 0.826 0.00234 0.821 0.830
## 48 19203 1006 0.785 0.00255 0.780 0.790
## 60 17682 802 0.752 0.00270 0.747 0.757
## 120 3 2472 0.544 0.01943 0.507 0.583
##
## YEAR_OF_DIAGNOSIS=2009
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 25522 1877 0.934 0.00147 0.931 0.937
## 24 23287 1598 0.875 0.00199 0.871 0.879
## 36 21389 1246 0.827 0.00229 0.823 0.832
## 48 19775 1009 0.788 0.00250 0.783 0.793
## 60 18056 860 0.753 0.00266 0.748 0.758
##
## YEAR_OF_DIAGNOSIS=2010
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 25762 1960 0.932 0.00148 0.929 0.935
## 24 23583 1498 0.877 0.00196 0.873 0.881
## 36 21704 1283 0.829 0.00227 0.824 0.833
## 48 19856 1007 0.789 0.00248 0.785 0.794
## 60 17634 931 0.751 0.00266 0.746 0.756
##
## YEAR_OF_DIAGNOSIS=2011
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 26669 1936 0.935 0.00142 0.932 0.938
## 24 24139 1711 0.874 0.00195 0.870 0.878
## 36 21935 1353 0.824 0.00226 0.820 0.829
## 48 19519 1101 0.782 0.00248 0.777 0.787
## 60 15871 866 0.745 0.00267 0.739 0.750
##
## YEAR_OF_DIAGNOSIS=2012
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 27096 2010 0.934 0.00141 0.932 0.937
## 24 24362 1591 0.878 0.00191 0.874 0.882
## 36 21745 1319 0.829 0.00223 0.825 0.834
## 48 18039 1008 0.789 0.00246 0.784 0.794
## 60 7642 659 0.751 0.00277 0.746 0.757
##
## YEAR_OF_DIAGNOSIS=2013
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 28214 2136 0.934 0.00138 0.932 0.937
## 24 24913 1639 0.878 0.00187 0.874 0.882
## 36 20818 1294 0.830 0.00219 0.826 0.834
## 48 9263 929 0.782 0.00259 0.777 0.788
## 60 7 288 0.630 0.03382 0.567 0.700
##
## YEAR_OF_DIAGNOSIS=2014
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 28519 2126 0.936 0.00134 0.934 0.939
## 24 23349 1530 0.883 0.00183 0.879 0.886
## 36 10284 1074 0.831 0.00234 0.827 0.836
## 48 7 343 0.653 0.04472 0.571 0.746
##
## YEAR_OF_DIAGNOSIS=2015
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 27931 2080 0.939 0.00129 0.937 0.942
## 24 11935 1351 0.880 0.00201 0.876 0.884
## 36 8 409 0.693 0.03072 0.635 0.756
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: YEAR_OF_DIAGNOSIS
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ YEAR_OF_DIAGNOSIS, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## YEAR_OF_DIAGNOSIS2005 -0.02829 0.97210 0.01540 -1.838 0.066132 .
## YEAR_OF_DIAGNOSIS2006 0.04329 1.04424 0.01545 2.802 0.005084 **
## YEAR_OF_DIAGNOSIS2007 0.05790 1.05961 0.01555 3.722 0.000197 ***
## YEAR_OF_DIAGNOSIS2008 0.11329 1.11995 0.01557 7.276 3.45e-13 ***
## YEAR_OF_DIAGNOSIS2009 0.10857 1.11469 0.01578 6.880 5.97e-12 ***
## YEAR_OF_DIAGNOSIS2010 0.12528 1.13347 0.01605 7.807 5.88e-15 ***
## YEAR_OF_DIAGNOSIS2011 0.15966 1.17311 0.01625 9.823 < 2e-16 ***
## YEAR_OF_DIAGNOSIS2012 0.12014 1.12765 0.01688 7.119 1.09e-12 ***
## YEAR_OF_DIAGNOSIS2013 0.14330 1.15408 0.01732 8.275 < 2e-16 ***
## YEAR_OF_DIAGNOSIS2014 0.12010 1.12760 0.01849 6.494 8.38e-11 ***
## YEAR_OF_DIAGNOSIS2015 0.12723 1.13568 0.02030 6.267 3.68e-10 ***
## YEAR_OF_DIAGNOSIS2016 NA NA 0.00000 NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## YEAR_OF_DIAGNOSIS2005 0.9721 1.0287 0.9432 1.002
## YEAR_OF_DIAGNOSIS2006 1.0442 0.9576 1.0131 1.076
## YEAR_OF_DIAGNOSIS2007 1.0596 0.9437 1.0278 1.092
## YEAR_OF_DIAGNOSIS2008 1.1200 0.8929 1.0863 1.155
## YEAR_OF_DIAGNOSIS2009 1.1147 0.8971 1.0807 1.150
## YEAR_OF_DIAGNOSIS2010 1.1335 0.8822 1.0984 1.170
## YEAR_OF_DIAGNOSIS2011 1.1731 0.8524 1.1363 1.211
## YEAR_OF_DIAGNOSIS2012 1.1277 0.8868 1.0910 1.166
## YEAR_OF_DIAGNOSIS2013 1.1541 0.8665 1.1156 1.194
## YEAR_OF_DIAGNOSIS2014 1.1276 0.8868 1.0875 1.169
## YEAR_OF_DIAGNOSIS2015 1.1357 0.8805 1.0914 1.182
## YEAR_OF_DIAGNOSIS2016 NA NA NA NA
##
## Concordance= 0.511 (se = 0.001 )
## Rsquare= 0.001 (max possible= 0.998 )
## Likelihood ratio test= 264 on 11 df, p=0
## Wald test = 260 on 11 df, p=0
## Score (logrank) test = 260.3 on 11 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: YEAR_OF_DIAGNOSIS
Primary Site
uni_var(test_var = "SITE_TEXT", data_imp = data)
## _________________________________________________
##
## ## SITE_TEXT
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SITE_TEXT, data = data)
##
## n events
## SITE_TEXT=C44.0 Skin of lip, NOS 631 187
## SITE_TEXT=C44.1 Eyelid 1184 380
## SITE_TEXT=C44.2 External ear 10639 3149
## SITE_TEXT=C44.3 Skin of ear and unspecified parts of face 33680 10586
## SITE_TEXT=C44.4 Skin of scalp and neck 30276 9995
## SITE_TEXT=C44.5 Skin of trunk 113276 23471
## SITE_TEXT=C44.6 Skin of upper limb and shoulder 90064 19354
## SITE_TEXT=C44.7 Skin of lower limb and hip 67737 12311
## SITE_TEXT=C44.8 Overlapping lesion of skin 389 143
## SITE_TEXT=C44.9 Skin, NOS 15034 10396
## median 0.95LCL
## SITE_TEXT=C44.0 Skin of lip, NOS 155 118.2
## SITE_TEXT=C44.1 Eyelid 122 109.5
## SITE_TEXT=C44.2 External ear 131 125.6
## SITE_TEXT=C44.3 Skin of ear and unspecified parts of face 118 115.7
## SITE_TEXT=C44.4 Skin of scalp and neck 114 111.1
## SITE_TEXT=C44.5 Skin of trunk NA NA
## SITE_TEXT=C44.6 Skin of upper limb and shoulder 164 162.7
## SITE_TEXT=C44.7 Skin of lower limb and hip NA NA
## SITE_TEXT=C44.8 Overlapping lesion of skin 113 87.0
## SITE_TEXT=C44.9 Skin, NOS 11 10.6
## 0.95UCL
## SITE_TEXT=C44.0 Skin of lip, NOS NA
## SITE_TEXT=C44.1 Eyelid 139.3
## SITE_TEXT=C44.2 External ear 138.2
## SITE_TEXT=C44.3 Skin of ear and unspecified parts of face 121.2
## SITE_TEXT=C44.4 Skin of scalp and neck 116.7
## SITE_TEXT=C44.5 Skin of trunk NA
## SITE_TEXT=C44.6 Skin of upper limb and shoulder NA
## SITE_TEXT=C44.7 Skin of lower limb and hip NA
## SITE_TEXT=C44.8 Overlapping lesion of skin NA
## SITE_TEXT=C44.9 Skin, NOS 11.5
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SITE_TEXT, data = data)
##
## SITE_TEXT=C44.0 Skin of lip, NOS
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 535 36 0.940 0.00971 0.921 0.959
## 24 467 37 0.873 0.01394 0.846 0.901
## 36 391 31 0.812 0.01673 0.780 0.845
## 48 312 21 0.764 0.01871 0.728 0.802
## 60 253 21 0.710 0.02085 0.670 0.752
## 120 53 38 0.541 0.03086 0.484 0.605
##
## SITE_TEXT=C44.1 Eyelid
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1026 60 0.947 0.00669 0.934 0.960
## 24 862 78 0.872 0.01021 0.852 0.892
## 36 714 55 0.813 0.01224 0.789 0.837
## 48 582 49 0.754 0.01397 0.727 0.782
## 60 473 42 0.696 0.01551 0.666 0.727
## 120 105 86 0.503 0.02240 0.461 0.549
##
## SITE_TEXT=C44.2 External ear
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 9051 556 0.945 0.00229 0.940 0.949
## 24 7649 612 0.878 0.00336 0.871 0.884
## 36 6310 499 0.817 0.00409 0.809 0.825
## 48 5107 412 0.760 0.00467 0.751 0.769
## 60 4109 269 0.716 0.00510 0.707 0.727
## 120 905 711 0.526 0.00766 0.511 0.541
##
## SITE_TEXT=C44.3 Skin of ear and unspecified parts of face
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 28750 1761 0.945 0.00128 0.942 0.947
## 24 24359 2104 0.873 0.00192 0.869 0.876
## 36 19836 1673 0.809 0.00233 0.804 0.813
## 48 16060 1335 0.750 0.00266 0.745 0.756
## 60 12693 1078 0.696 0.00294 0.690 0.702
## 120 2658 2351 0.494 0.00437 0.486 0.503
##
## SITE_TEXT=C44.4 Skin of scalp and neck
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 25477 2029 0.929 0.00152 0.926 0.932
## 24 21131 2204 0.845 0.00219 0.841 0.850
## 36 16769 1763 0.770 0.00263 0.765 0.775
## 48 13283 1211 0.710 0.00294 0.704 0.716
## 60 10447 850 0.661 0.00319 0.654 0.667
## 120 2165 1788 0.483 0.00459 0.474 0.492
##
## SITE_TEXT=C44.5 Skin of trunk
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 96604 4575 0.957 0.000622 0.956 0.958
## 24 83748 4741 0.908 0.000911 0.906 0.910
## 36 69838 3766 0.865 0.001110 0.862 0.867
## 48 58021 2849 0.827 0.001267 0.824 0.829
## 60 47338 2011 0.796 0.001397 0.793 0.798
## 120 11762 4872 0.667 0.002168 0.662 0.671
##
## SITE_TEXT=C44.6 Skin of upper limb and shoulder
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 77412 3180 0.962 0.000654 0.961 0.964
## 24 67145 3771 0.914 0.000994 0.912 0.916
## 36 55975 3084 0.869 0.001230 0.866 0.871
## 48 46240 2311 0.830 0.001414 0.827 0.833
## 60 37565 1791 0.795 0.001577 0.792 0.798
## 120 8927 4580 0.641 0.002558 0.636 0.646
##
## SITE_TEXT=C44.7 Skin of lower limb and hip
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 58436 2223 0.965 0.000727 0.964 0.967
## 24 50972 2547 0.921 0.001096 0.919 0.923
## 36 42817 2116 0.881 0.001359 0.878 0.883
## 48 35910 1459 0.849 0.001549 0.845 0.852
## 60 29399 1163 0.819 0.001724 0.815 0.822
## 120 7556 2467 0.711 0.002634 0.706 0.717
##
## SITE_TEXT=C44.8 Overlapping lesion of skin
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 307 52 0.860 0.0180 0.826 0.896
## 24 262 23 0.794 0.0213 0.754 0.837
## 36 218 21 0.727 0.0240 0.682 0.776
## 48 172 11 0.688 0.0254 0.640 0.740
## 60 144 8 0.653 0.0269 0.603 0.708
## 120 29 26 0.473 0.0388 0.402 0.555
##
## SITE_TEXT=C44.9 Skin, NOS
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6559 7475 0.484 0.00418 0.476 0.492
## 24 4464 1506 0.368 0.00411 0.360 0.376
## 36 3211 643 0.311 0.00405 0.303 0.319
## 48 2447 291 0.280 0.00403 0.273 0.288
## 60 1881 177 0.258 0.00404 0.251 0.266
## 120 412 270 0.201 0.00460 0.192 0.210
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: SITE_TEXT
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SITE_TEXT, data = data)
##
## n= 362910, number of events= 89972
##
## coef
## SITE_TEXTC44.1 Eyelid 0.08145
## SITE_TEXTC44.2 External ear 0.02387
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 0.09618
## SITE_TEXTC44.4 Skin of scalp and neck 0.19201
## SITE_TEXTC44.5 Skin of trunk -0.38193
## SITE_TEXTC44.6 Skin of upper limb and shoulder -0.34458
## SITE_TEXTC44.7 Skin of lower limb and hip -0.53944
## SITE_TEXTC44.8 Overlapping lesion of skin 0.30726
## SITE_TEXTC44.9 Skin, NOS 1.67933
## exp(coef)
## SITE_TEXTC44.1 Eyelid 1.08485
## SITE_TEXTC44.2 External ear 1.02416
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 1.10095
## SITE_TEXTC44.4 Skin of scalp and neck 1.21168
## SITE_TEXTC44.5 Skin of trunk 0.68254
## SITE_TEXTC44.6 Skin of upper limb and shoulder 0.70852
## SITE_TEXTC44.7 Skin of lower limb and hip 0.58308
## SITE_TEXTC44.8 Overlapping lesion of skin 1.35970
## SITE_TEXTC44.9 Skin, NOS 5.36195
## se(coef) z
## SITE_TEXTC44.1 Eyelid 0.08933 0.912
## SITE_TEXTC44.2 External ear 0.07527 0.317
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 0.07377 1.304
## SITE_TEXTC44.4 Skin of scalp and neck 0.07381 2.601
## SITE_TEXTC44.5 Skin of trunk 0.07342 -5.202
## SITE_TEXTC44.6 Skin of upper limb and shoulder 0.07348 -4.689
## SITE_TEXTC44.7 Skin of lower limb and hip 0.07368 -7.321
## SITE_TEXTC44.8 Overlapping lesion of skin 0.11109 2.766
## SITE_TEXTC44.9 Skin, NOS 0.07379 22.758
## Pr(>|z|)
## SITE_TEXTC44.1 Eyelid 0.36189
## SITE_TEXTC44.2 External ear 0.75110
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 0.19233
## SITE_TEXTC44.4 Skin of scalp and neck 0.00928 **
## SITE_TEXTC44.5 Skin of trunk 1.97e-07 ***
## SITE_TEXTC44.6 Skin of upper limb and shoulder 2.74e-06 ***
## SITE_TEXTC44.7 Skin of lower limb and hip 2.46e-13 ***
## SITE_TEXTC44.8 Overlapping lesion of skin 0.00568 **
## SITE_TEXTC44.9 Skin, NOS < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef)
## SITE_TEXTC44.1 Eyelid 1.0849
## SITE_TEXTC44.2 External ear 1.0242
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 1.1010
## SITE_TEXTC44.4 Skin of scalp and neck 1.2117
## SITE_TEXTC44.5 Skin of trunk 0.6825
## SITE_TEXTC44.6 Skin of upper limb and shoulder 0.7085
## SITE_TEXTC44.7 Skin of lower limb and hip 0.5831
## SITE_TEXTC44.8 Overlapping lesion of skin 1.3597
## SITE_TEXTC44.9 Skin, NOS 5.3620
## exp(-coef)
## SITE_TEXTC44.1 Eyelid 0.9218
## SITE_TEXTC44.2 External ear 0.9764
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 0.9083
## SITE_TEXTC44.4 Skin of scalp and neck 0.8253
## SITE_TEXTC44.5 Skin of trunk 1.4651
## SITE_TEXTC44.6 Skin of upper limb and shoulder 1.4114
## SITE_TEXTC44.7 Skin of lower limb and hip 1.7150
## SITE_TEXTC44.8 Overlapping lesion of skin 0.7355
## SITE_TEXTC44.9 Skin, NOS 0.1865
## lower .95
## SITE_TEXTC44.1 Eyelid 0.9106
## SITE_TEXTC44.2 External ear 0.8837
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 0.9527
## SITE_TEXTC44.4 Skin of scalp and neck 1.0485
## SITE_TEXTC44.5 Skin of trunk 0.5911
## SITE_TEXTC44.6 Skin of upper limb and shoulder 0.6135
## SITE_TEXTC44.7 Skin of lower limb and hip 0.5047
## SITE_TEXTC44.8 Overlapping lesion of skin 1.0937
## SITE_TEXTC44.9 Skin, NOS 4.6399
## upper .95
## SITE_TEXTC44.1 Eyelid 1.2924
## SITE_TEXTC44.2 External ear 1.1870
## SITE_TEXTC44.3 Skin of ear and unspecified parts of face 1.2722
## SITE_TEXTC44.4 Skin of scalp and neck 1.4003
## SITE_TEXTC44.5 Skin of trunk 0.7882
## SITE_TEXTC44.6 Skin of upper limb and shoulder 0.8183
## SITE_TEXTC44.7 Skin of lower limb and hip 0.6737
## SITE_TEXTC44.8 Overlapping lesion of skin 1.6904
## SITE_TEXTC44.9 Skin, NOS 6.1963
##
## Concordance= 0.617 (se = 0.001 )
## Rsquare= 0.07 (max possible= 0.998 )
## Likelihood ratio test= 26455 on 9 df, p=0
## Wald test = 38543 on 9 df, p=0
## Score (logrank) test = 51507 on 9 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: SITE_TEXT
Histology
uni_var(test_var = "HISTOLOGY_F_LIM", data_imp = data)
## _________________________________________________
##
## ## HISTOLOGY_F_LIM
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ HISTOLOGY_F_LIM, data = data)
##
## n events median 0.95LCL 0.95UCL
## HISTOLOGY_F_LIM=8720 182616 49264 162.7 160.3 165.2
## HISTOLOGY_F_LIM=8743 112470 17259 NA NA NA
## HISTOLOGY_F_LIM=8742 19251 4953 129.7 125.6 133.9
## HISTOLOGY_F_LIM=Other 48573 18496 95.9 93.1 97.9
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ HISTOLOGY_F_LIM, data = data)
##
## HISTOLOGY_F_LIM=8720
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 149938 14977 0.914 0.000673 0.913 0.915
## 24 129130 9114 0.856 0.000861 0.855 0.858
## 36 108073 6738 0.809 0.000988 0.807 0.811
## 48 89985 4912 0.770 0.001088 0.767 0.772
## 60 73642 3670 0.736 0.001175 0.733 0.738
## 120 18210 8710 0.600 0.001712 0.597 0.603
##
## HISTOLOGY_F_LIM=8743
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 97178 2303 0.978 0.000454 0.977 0.979
## 24 84928 3105 0.945 0.000726 0.944 0.947
## 36 70760 2841 0.911 0.000939 0.909 0.913
## 48 58608 2255 0.880 0.001115 0.878 0.882
## 60 47353 1812 0.850 0.001278 0.848 0.853
## 120 11407 4355 0.724 0.002196 0.720 0.728
##
## HISTOLOGY_F_LIM=8742
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 16438 630 0.965 0.00137 0.962 0.968
## 24 14192 813 0.915 0.00215 0.911 0.919
## 36 11594 790 0.860 0.00276 0.855 0.866
## 48 9298 676 0.806 0.00329 0.800 0.812
## 60 7377 506 0.758 0.00372 0.751 0.766
## 120 1477 1368 0.530 0.00623 0.518 0.543
##
## HISTOLOGY_F_LIM=Other
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 40603 4037 0.913 0.00131 0.910 0.915
## 24 32809 4591 0.806 0.00189 0.802 0.809
## 36 25652 3282 0.720 0.00220 0.715 0.724
## 48 20243 2106 0.656 0.00240 0.652 0.661
## 60 15930 1422 0.607 0.00256 0.602 0.612
## 120 3478 2756 0.447 0.00341 0.441 0.454
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: HISTOLOGY_F_LIM
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ HISTOLOGY_F_LIM, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## HISTOLOGY_F_LIM9680 NA NA 0.000000 NA NA
## HISTOLOGY_F_LIM8743 -0.609418 0.543667 0.008846 -68.895 <2e-16 ***
## HISTOLOGY_F_LIM8742 -0.033942 0.966628 0.014909 -2.277 0.0228 *
## HISTOLOGY_F_LIMOther 0.439458 1.551866 0.008632 50.911 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## HISTOLOGY_F_LIM9680 NA NA NA NA
## HISTOLOGY_F_LIM8743 0.5437 1.8394 0.5343 0.5532
## HISTOLOGY_F_LIM8742 0.9666 1.0345 0.9388 0.9953
## HISTOLOGY_F_LIMOther 1.5519 0.6444 1.5258 1.5783
##
## Concordance= 0.599 (se = 0.001 )
## Rsquare= 0.028 (max possible= 0.998 )
## Likelihood ratio test= 10352 on 3 df, p=0
## Wald test = 9905 on 3 df, p=0
## Score (logrank) test = 10430 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: HISTOLOGY_F_LIM
Grade
uni_var(test_var = "GRADE_F", data_imp = data)
## _________________________________________________
##
## ## GRADE_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ GRADE_F, data = data)
##
## n events median 0.95LCL 0.95UCL
## GRADE_F=Gr I: Well Diff 759 178 NA 140.5 NA
## GRADE_F=Gr II: Mod Diff 1064 243 NA 156.6 NA
## GRADE_F=Gr III: Poor Diff 1877 975 46.8 40.9 55.1
## GRADE_F=Gr IV: Undiff/Anaplastic 665 287 73.0 59.9 101.7
## GRADE_F=NA/Unkown 358545 88289 164.5 161.9 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ GRADE_F, data = data)
##
## GRADE_F=Gr I: Well Diff
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 641 33 0.953 0.00793 0.938 0.969
## 24 540 39 0.892 0.01203 0.869 0.916
## 36 437 28 0.842 0.01464 0.814 0.871
## 48 346 14 0.812 0.01620 0.781 0.844
## 60 292 15 0.774 0.01816 0.739 0.810
## 120 73 45 0.602 0.02816 0.549 0.660
##
## GRADE_F=Gr II: Mod Diff
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 925 41 0.959 0.00630 0.947 0.971
## 24 814 53 0.902 0.00962 0.883 0.921
## 36 695 36 0.860 0.01148 0.837 0.882
## 48 600 22 0.831 0.01259 0.807 0.856
## 60 506 22 0.799 0.01386 0.772 0.827
## 120 140 64 0.654 0.02061 0.615 0.696
##
## GRADE_F=Gr III: Poor Diff
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1287 456 0.748 0.0102 0.728 0.768
## 24 968 211 0.620 0.0117 0.598 0.644
## 36 770 104 0.550 0.0122 0.527 0.574
## 48 615 73 0.495 0.0126 0.471 0.520
## 60 495 34 0.466 0.0128 0.441 0.491
## 120 114 85 0.351 0.0151 0.322 0.382
##
## GRADE_F=Gr IV: Undiff/Anaplastic
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 492 111 0.824 0.0152 0.795 0.854
## 24 385 62 0.715 0.0185 0.680 0.752
## 36 297 42 0.630 0.0204 0.592 0.672
## 48 243 23 0.579 0.0214 0.539 0.623
## 60 198 15 0.541 0.0221 0.500 0.586
## 120 44 32 0.401 0.0289 0.348 0.462
##
## GRADE_F=NA/Unkown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 300812 21306 0.937 0.000416 0.937 0.938
## 24 258352 17258 0.881 0.000570 0.880 0.882
## 36 213880 13441 0.832 0.000677 0.831 0.834
## 48 176330 9817 0.791 0.000760 0.790 0.793
## 60 142811 7324 0.756 0.000832 0.754 0.757
## 120 34201 16963 0.614 0.001257 0.612 0.617
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: GRADE_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ GRADE_F, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z
## GRADE_FGr II: Mod Diff -0.15501 0.85640 0.09866 -1.571
## GRADE_FGr III: Poor Diff 1.08725 2.96610 0.08151 13.339
## GRADE_FGr IV: Undiff/Anaplastic 0.81123 2.25069 0.09541 8.503
## GRADE_F5 NA NA 0.00000 NA
## GRADE_F6 NA NA 0.00000 NA
## GRADE_F7 NA NA 0.00000 NA
## GRADE_F8 NA NA 0.00000 NA
## GRADE_FNA/Unkown 0.03965 1.04044 0.07503 0.528
## Pr(>|z|)
## GRADE_FGr II: Mod Diff 0.116
## GRADE_FGr III: Poor Diff <2e-16 ***
## GRADE_FGr IV: Undiff/Anaplastic <2e-16 ***
## GRADE_F5 NA
## GRADE_F6 NA
## GRADE_F7 NA
## GRADE_F8 NA
## GRADE_FNA/Unkown 0.597
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## GRADE_FGr II: Mod Diff 0.8564 1.1677 0.7058 1.039
## GRADE_FGr III: Poor Diff 2.9661 0.3371 2.5282 3.480
## GRADE_FGr IV: Undiff/Anaplastic 2.2507 0.4443 1.8668 2.713
## GRADE_F5 NA NA NA NA
## GRADE_F6 NA NA NA NA
## GRADE_F7 NA NA NA NA
## GRADE_F8 NA NA NA NA
## GRADE_FNA/Unkown 1.0404 0.9611 0.8982 1.205
##
## Concordance= 0.506 (se = 0 )
## Rsquare= 0.003 (max possible= 0.998 )
## Likelihood ratio test= 915.1 on 4 df, p=0
## Wald test = 1234 on 4 df, p=0
## Score (logrank) test = 1343 on 4 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: GRADE_F
Clinical T Stage
uni_var(test_var = "TNM_CLIN_T", data_imp = data)
## _________________________________________________
##
## ## TNM_CLIN_T
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_T, data = data)
##
## 9794 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_CLIN_T=N_A 1608 548 160.3 150.7 NA
## TNM_CLIN_T=c0 4261 2744 14.1 12.7 15.3
## TNM_CLIN_T=c1 18911 2882 NA NA NA
## TNM_CLIN_T=c1A 55175 4305 95.5 95.5 NA
## TNM_CLIN_T=c1B 20634 2001 97.1 NA NA
## TNM_CLIN_T=c2 5403 1306 153.7 141.8 NA
## TNM_CLIN_T=c2A 34068 5945 164.4 162.0 NA
## TNM_CLIN_T=c2B 8717 2535 110.8 104.6 122.2
## TNM_CLIN_T=c3 3178 1210 89.6 81.8 96.4
## TNM_CLIN_T=c3A 13377 3947 113.4 109.1 118.6
## TNM_CLIN_T=c3B 10395 4261 69.7 66.3 72.0
## TNM_CLIN_T=c4 2170 1190 41.9 37.9 45.3
## TNM_CLIN_T=c4A 6281 2644 70.0 65.6 74.2
## TNM_CLIN_T=c4B 10655 6264 34.2 32.9 35.4
## TNM_CLIN_T=cX 155744 45656 165.4 164.6 NA
## TNM_CLIN_T=pIS 2539 465 NA 157.9 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_T, data = data)
##
## 9794 observations deleted due to missingness
## TNM_CLIN_T=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1405 113 0.928 0.00655 0.915 0.941
## 24 1274 98 0.862 0.00883 0.845 0.880
## 36 1170 67 0.816 0.00998 0.797 0.836
## 48 1073 61 0.773 0.01089 0.752 0.794
## 60 986 40 0.743 0.01142 0.721 0.766
## 120 400 138 0.619 0.01375 0.593 0.647
##
## TNM_CLIN_T=c0
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2014 1958 0.524 0.00783 0.509 0.540
## 24 1383 415 0.410 0.00788 0.395 0.426
## 36 980 177 0.353 0.00788 0.338 0.369
## 48 726 84 0.320 0.00793 0.305 0.336
## 60 530 40 0.300 0.00804 0.285 0.316
## 120 87 59 0.242 0.00993 0.224 0.263
##
## TNM_CLIN_T=c1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 16419 403 0.977 0.00112 0.975 0.979
## 24 14824 460 0.949 0.00170 0.946 0.952
## 36 12980 464 0.918 0.00218 0.913 0.922
## 48 11002 352 0.891 0.00253 0.886 0.896
## 60 8896 316 0.863 0.00290 0.857 0.869
## 120 1502 801 0.720 0.00579 0.709 0.732
##
## TNM_CLIN_T=c1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 45816 779 0.984 0.000555 0.983 0.986
## 24 38151 945 0.963 0.000888 0.961 0.964
## 36 28525 852 0.938 0.001198 0.936 0.941
## 48 19945 721 0.910 0.001552 0.907 0.913
## 60 12428 513 0.881 0.001964 0.878 0.885
##
## TNM_CLIN_T=c1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 17122 385 0.980 0.00103 0.978 0.982
## 24 13908 510 0.948 0.00170 0.945 0.951
## 36 9901 420 0.915 0.00229 0.910 0.919
## 48 6635 305 0.881 0.00291 0.876 0.887
## 60 3871 204 0.847 0.00367 0.840 0.854
##
## TNM_CLIN_T=c2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4665 211 0.959 0.00280 0.953 0.964
## 24 4129 242 0.907 0.00417 0.899 0.915
## 36 3503 212 0.858 0.00513 0.848 0.868
## 48 2947 168 0.814 0.00587 0.803 0.826
## 60 2326 161 0.766 0.00665 0.753 0.779
## 120 303 287 0.592 0.01193 0.569 0.616
##
## TNM_CLIN_T=c2A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 29464 759 0.976 0.000856 0.974 0.978
## 24 25227 1136 0.936 0.001419 0.934 0.939
## 36 20248 1037 0.894 0.001862 0.891 0.898
## 48 16002 862 0.853 0.002255 0.848 0.857
## 60 12260 680 0.812 0.002631 0.807 0.817
## 120 1826 1343 0.645 0.005145 0.635 0.656
##
## TNM_CLIN_T=c2B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7387 437 0.947 0.00249 0.942 0.951
## 24 6074 590 0.867 0.00387 0.860 0.875
## 36 4657 499 0.790 0.00485 0.780 0.799
## 48 3501 345 0.725 0.00556 0.714 0.736
## 60 2540 243 0.669 0.00619 0.657 0.681
## 120 314 391 0.483 0.01043 0.463 0.503
##
## TNM_CLIN_T=c3
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2678 250 0.917 0.00500 0.908 0.927
## 24 2266 256 0.827 0.00700 0.814 0.841
## 36 1815 232 0.738 0.00836 0.722 0.754
## 48 1412 162 0.667 0.00922 0.650 0.686
## 60 1070 114 0.609 0.00992 0.590 0.629
## 120 129 188 0.425 0.01512 0.397 0.456
##
## TNM_CLIN_T=c3A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 11497 582 0.954 0.00187 0.950 0.957
## 24 9564 878 0.878 0.00301 0.872 0.884
## 36 7351 784 0.799 0.00383 0.792 0.807
## 48 5649 573 0.731 0.00444 0.723 0.740
## 60 4221 389 0.676 0.00492 0.666 0.685
## 120 589 689 0.479 0.00826 0.463 0.495
##
## TNM_CLIN_T=c3B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 8723 818 0.917 0.00277 0.912 0.923
## 24 6761 1160 0.789 0.00423 0.781 0.798
## 36 4905 859 0.681 0.00503 0.671 0.690
## 48 3581 530 0.600 0.00552 0.590 0.611
## 60 2570 328 0.539 0.00591 0.528 0.551
## 120 295 527 0.344 0.00888 0.327 0.362
##
## TNM_CLIN_T=c4
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1605 425 0.797 0.00882 0.780 0.814
## 24 1184 310 0.637 0.01075 0.616 0.659
## 36 889 178 0.537 0.01140 0.515 0.560
## 48 662 113 0.464 0.01175 0.441 0.487
## 60 501 67 0.413 0.01199 0.390 0.437
## 120 59 95 0.280 0.01600 0.250 0.313
##
## TNM_CLIN_T=c4A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5224 580 0.904 0.00380 0.896 0.911
## 24 4043 712 0.775 0.00554 0.764 0.786
## 36 3049 475 0.677 0.00641 0.665 0.690
## 48 2280 334 0.597 0.00700 0.583 0.611
## 60 1651 210 0.536 0.00745 0.521 0.551
## 120 226 318 0.360 0.01061 0.339 0.381
##
## TNM_CLIN_T=c4B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 8023 2025 0.804 0.00392 0.796 0.811
## 24 5505 1854 0.610 0.00493 0.600 0.620
## 36 3705 1051 0.485 0.00522 0.475 0.495
## 48 2521 581 0.401 0.00536 0.391 0.412
## 60 1742 299 0.349 0.00546 0.338 0.359
## 120 160 444 0.194 0.00736 0.180 0.209
##
## TNM_CLIN_T=cX
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 132133 11393 0.924 0.000686 0.923 0.925
## 24 119023 7409 0.871 0.000881 0.869 0.873
## 36 106890 5972 0.826 0.001009 0.824 0.828
## 48 96220 4458 0.791 0.001097 0.788 0.793
## 60 86053 3647 0.760 0.001168 0.757 0.762
## 120 28530 11018 0.630 0.001528 0.627 0.633
##
## TNM_CLIN_T=pIS
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2192 63 0.974 0.00329 0.967 0.980
## 24 1850 88 0.932 0.00536 0.922 0.943
## 36 1493 77 0.890 0.00697 0.876 0.903
## 48 1164 66 0.847 0.00841 0.830 0.863
## 60 892 49 0.807 0.00975 0.788 0.826
## 120 152 115 0.623 0.01838 0.588 0.660
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_CLIN_T
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_T, data = data)
##
## n= 353116, number of events= 87903
## (9794 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_CLIN_Tc0 1.70956 5.52651 0.04684 36.494 < 2e-16 ***
## TNM_CLIN_Tc1 -0.57711 0.56152 0.04662 -12.379 < 2e-16 ***
## TNM_CLIN_Tc1A -0.89914 0.40692 0.04543 -19.792 < 2e-16 ***
## TNM_CLIN_Tc1B -0.63446 0.53022 0.04829 -13.138 < 2e-16 ***
## TNM_CLIN_Tc2 -0.06001 0.94175 0.05092 -1.179 0.239
## TNM_CLIN_Tc2A -0.31573 0.72926 0.04467 -7.068 1.57e-12 ***
## TNM_CLIN_Tc2B 0.29119 1.33802 0.04715 6.176 6.57e-10 ***
## TNM_CLIN_Tc2C NA NA 0.00000 NA NA
## TNM_CLIN_Tc3 0.51767 1.67811 0.05152 10.048 < 2e-16 ***
## TNM_CLIN_Tc3A 0.26915 1.30885 0.04562 5.900 3.64e-09 ***
## TNM_CLIN_Tc3B 0.71220 2.03847 0.04543 15.677 < 2e-16 ***
## TNM_CLIN_Tc4 1.10491 3.01896 0.05166 21.387 < 2e-16 ***
## TNM_CLIN_Tc4A 0.71881 2.05200 0.04698 15.302 < 2e-16 ***
## TNM_CLIN_Tc4B 1.28103 3.60035 0.04461 28.714 < 2e-16 ***
## TNM_CLIN_TcX -0.05344 0.94796 0.04298 -1.243 0.214
## TNM_CLIN_TpIS -0.26369 0.76821 0.06307 -4.181 2.90e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_CLIN_Tc0 5.5265 0.1809 5.0417 6.0579
## TNM_CLIN_Tc1 0.5615 1.7809 0.5125 0.6152
## TNM_CLIN_Tc1A 0.4069 2.4575 0.3723 0.4448
## TNM_CLIN_Tc1B 0.5302 1.8860 0.4823 0.5829
## TNM_CLIN_Tc2 0.9418 1.0619 0.8523 1.0406
## TNM_CLIN_Tc2A 0.7293 1.3713 0.6681 0.7960
## TNM_CLIN_Tc2B 1.3380 0.7474 1.2199 1.4676
## TNM_CLIN_Tc2C NA NA NA NA
## TNM_CLIN_Tc3 1.6781 0.5959 1.5169 1.8564
## TNM_CLIN_Tc3A 1.3089 0.7640 1.1969 1.4313
## TNM_CLIN_Tc3B 2.0385 0.4906 1.8648 2.2283
## TNM_CLIN_Tc4 3.0190 0.3312 2.7282 3.3407
## TNM_CLIN_Tc4A 2.0520 0.4873 1.8715 2.2499
## TNM_CLIN_Tc4B 3.6004 0.2778 3.2989 3.9293
## TNM_CLIN_TcX 0.9480 1.0549 0.8714 1.0313
## TNM_CLIN_TpIS 0.7682 1.3017 0.6789 0.8693
##
## Concordance= 0.64 (se = 0.001 )
## Rsquare= 0.066 (max possible= 0.998 )
## Likelihood ratio test= 24210 on 15 df, p=0
## Wald test = 28661 on 15 df, p=0
## Score (logrank) test = 34935 on 15 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_CLIN_T
Clinical N Stage
uni_var(test_var = "TNM_CLIN_N", data_imp = data)
## _________________________________________________
##
## ## TNM_CLIN_N
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_N, data = data)
##
## 8298 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_CLIN_N=N_A 1608 548 160.3 150.7 NA
## TNM_CLIN_N=c0 247096 47331 NA 164.6 NA
## TNM_CLIN_N=c1 5666 2838 43.6 40.5 47.0
## TNM_CLIN_N=c1A 1325 516 110.8 93.4 131.8
## TNM_CLIN_N=c1B 1624 954 28.6 26.1 33.0
## TNM_CLIN_N=c2 1148 630 33.9 31.3 39.2
## TNM_CLIN_N=c2A 415 186 77.7 67.0 118.9
## TNM_CLIN_N=c2B 805 487 29.2 26.1 33.3
## TNM_CLIN_N=c2C 900 479 38.7 35.5 45.7
## TNM_CLIN_N=c3 2603 1825 15.7 14.8 17.1
## TNM_CLIN_N=cX 91422 32280 155.9 153.6 158.2
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_N, data = data)
##
## 8298 observations deleted due to missingness
## TNM_CLIN_N=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1405 113 0.928 0.00655 0.915 0.941
## 24 1274 98 0.862 0.00883 0.845 0.880
## 36 1170 67 0.816 0.00998 0.797 0.836
## 48 1073 61 0.773 0.01089 0.752 0.794
## 60 986 40 0.743 0.01142 0.721 0.766
## 120 400 138 0.619 0.01375 0.593 0.647
##
## TNM_CLIN_N=c0
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 210265 8609 0.963 0.000394 0.962 0.964
## 24 179841 9675 0.916 0.000595 0.915 0.917
## 36 145477 8175 0.871 0.000746 0.870 0.873
## 48 116031 6081 0.831 0.000870 0.830 0.833
## 60 89945 4538 0.795 0.000983 0.794 0.797
## 120 14585 9384 0.646 0.001775 0.643 0.650
##
## TNM_CLIN_N=c1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3995 1271 0.767 0.00574 0.756 0.778
## 24 2926 691 0.628 0.00671 0.615 0.641
## 36 2138 385 0.539 0.00714 0.525 0.553
## 48 1585 206 0.483 0.00740 0.468 0.497
## 60 1145 117 0.443 0.00766 0.428 0.458
## 120 137 155 0.332 0.01086 0.311 0.354
##
## TNM_CLIN_N=c1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1160 95 0.926 0.00731 0.912 0.940
## 24 962 129 0.820 0.01092 0.799 0.842
## 36 797 96 0.735 0.01278 0.710 0.760
## 48 649 73 0.665 0.01396 0.638 0.693
## 60 524 43 0.617 0.01475 0.589 0.646
## 120 94 74 0.471 0.02050 0.432 0.513
##
## TNM_CLIN_N=c1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1085 442 0.719 0.0114 0.697 0.741
## 24 769 247 0.550 0.0128 0.525 0.575
## 36 553 115 0.462 0.0131 0.437 0.489
## 48 419 71 0.399 0.0133 0.373 0.426
## 60 330 22 0.376 0.0134 0.350 0.403
## 120 50 52 0.278 0.0165 0.248 0.312
##
## TNM_CLIN_N=c2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 814 256 0.769 0.0127 0.744 0.794
## 24 550 181 0.590 0.0152 0.561 0.621
## 36 383 89 0.486 0.0160 0.456 0.519
## 48 286 43 0.427 0.0164 0.396 0.461
## 60 217 26 0.386 0.0167 0.354 0.420
## 120 46 34 0.301 0.0194 0.265 0.341
##
## TNM_CLIN_N=c2A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 367 29 0.929 0.0128 0.904 0.954
## 24 286 62 0.767 0.0214 0.726 0.810
## 36 231 36 0.666 0.0244 0.620 0.716
## 48 200 13 0.627 0.0252 0.580 0.679
## 60 162 17 0.571 0.0264 0.522 0.626
## 120 26 27 0.411 0.0371 0.344 0.490
##
## TNM_CLIN_N=c2B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 576 199 0.748 0.0155 0.719 0.779
## 24 394 138 0.562 0.0180 0.528 0.598
## 36 287 73 0.454 0.0185 0.419 0.491
## 48 216 36 0.393 0.0186 0.358 0.431
## 60 160 16 0.361 0.0187 0.326 0.399
## 120 25 25 0.264 0.0232 0.222 0.314
##
## TNM_CLIN_N=c2C
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 687 155 0.822 0.0130 0.797 0.848
## 24 482 141 0.646 0.0167 0.614 0.679
## 36 332 82 0.527 0.0181 0.493 0.564
## 48 220 44 0.450 0.0188 0.415 0.489
## 60 153 23 0.396 0.0197 0.359 0.436
## 120 21 33 0.281 0.0231 0.239 0.330
##
## TNM_CLIN_N=c3
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1414 1077 0.576 0.00984 0.557 0.595
## 24 851 433 0.391 0.00993 0.372 0.411
## 36 570 154 0.314 0.00973 0.296 0.334
## 48 388 85 0.263 0.00961 0.245 0.283
## 60 279 27 0.243 0.00964 0.225 0.262
## 120 31 45 0.168 0.01312 0.145 0.196
##
## TNM_CLIN_N=cX
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 75826 8985 0.898 0.00102 0.896 0.900
## 24 67601 5322 0.834 0.00127 0.831 0.836
## 36 60464 4113 0.782 0.00143 0.779 0.785
## 48 54421 3020 0.742 0.00153 0.739 0.745
## 60 48736 2439 0.707 0.00161 0.704 0.711
## 120 19157 7130 0.577 0.00195 0.573 0.581
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_CLIN_N
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_N, data = data)
##
## n= 354612, number of events= 88074
## (8298 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_CLIN_Nc0 -0.23062 0.79404 0.04299 -5.365 8.12e-08 ***
## TNM_CLIN_Nc1 1.07883 2.94122 0.04671 23.098 < 2e-16 ***
## TNM_CLIN_Nc1A 0.43514 1.54518 0.06136 7.092 1.32e-12 ***
## TNM_CLIN_Nc1B 1.26262 3.53466 0.05363 23.541 < 2e-16 ***
## TNM_CLIN_Nc2 1.18426 3.26826 0.05845 20.262 < 2e-16 ***
## TNM_CLIN_Nc2A 0.60849 1.83766 0.08487 7.170 7.52e-13 ***
## TNM_CLIN_Nc2B 1.26659 3.54872 0.06231 20.328 < 2e-16 ***
## TNM_CLIN_Nc2C 1.13924 3.12438 0.06259 18.201 < 2e-16 ***
## TNM_CLIN_Nc3 1.76674 5.85177 0.04878 36.216 < 2e-16 ***
## TNM_CLIN_NcX 0.14286 1.15357 0.04308 3.316 0.000913 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_CLIN_Nc0 0.794 1.2594 0.7299 0.8638
## TNM_CLIN_Nc1 2.941 0.3400 2.6839 3.2232
## TNM_CLIN_Nc1A 1.545 0.6472 1.3701 1.7426
## TNM_CLIN_Nc1B 3.535 0.2829 3.1820 3.9265
## TNM_CLIN_Nc2 3.268 0.3060 2.9145 3.6649
## TNM_CLIN_Nc2A 1.838 0.5442 1.5560 2.1702
## TNM_CLIN_Nc2B 3.549 0.2818 3.1408 4.0096
## TNM_CLIN_Nc2C 3.124 0.3201 2.7637 3.5322
## TNM_CLIN_Nc3 5.852 0.1709 5.3182 6.4389
## TNM_CLIN_NcX 1.154 0.8669 1.0602 1.2552
##
## Concordance= 0.59 (se = 0.001 )
## Rsquare= 0.033 (max possible= 0.998 )
## Likelihood ratio test= 11826 on 10 df, p=0
## Wald test = 15960 on 10 df, p=0
## Score (logrank) test = 19080 on 10 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_CLIN_N
Clinical Stage Group
uni_var(test_var = "TNM_CLIN_STAGE_GROUP", data_imp = data)
## _________________________________________________
##
## ## TNM_CLIN_STAGE_GROUP
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_STAGE_GROUP, data = data)
##
## 43 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_CLIN_STAGE_GROUP=0 3415 657 NA 157.90 NA
## TNM_CLIN_STAGE_GROUP=1 11136 1745 NA 161.58 NA
## TNM_CLIN_STAGE_GROUP=1A 95569 10889 NA NA NA
## TNM_CLIN_STAGE_GROUP=1B 63589 9853 NA 164.44 NA
## TNM_CLIN_STAGE_GROUP=2 1978 608 151.26 117.19 NA
## TNM_CLIN_STAGE_GROUP=2A 22432 6304 118.54 113.81 123.4
## TNM_CLIN_STAGE_GROUP=2B 15534 6087 76.16 73.53 79.2
## TNM_CLIN_STAGE_GROUP=2C 7948 4304 42.45 40.54 43.9
## TNM_CLIN_STAGE_GROUP=3 11303 5144 61.27 58.78 64.8
## TNM_CLIN_STAGE_GROUP=4 13516 11322 6.41 6.18 6.6
## TNM_CLIN_STAGE_GROUP=N_A 1609 548 160.33 150.70 NA
## TNM_CLIN_STAGE_GROUP=99 114838 32497 164.47 161.68 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_STAGE_GROUP, data = data)
##
## 43 observations deleted due to missingness
## TNM_CLIN_STAGE_GROUP=0
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2944 109 0.966 0.00319 0.960 0.972
## 24 2494 122 0.924 0.00484 0.914 0.933
## 36 2032 101 0.883 0.00609 0.871 0.895
## 48 1633 88 0.842 0.00724 0.828 0.856
## 60 1294 64 0.806 0.00822 0.790 0.822
## 120 251 159 0.639 0.01461 0.611 0.668
##
## TNM_CLIN_STAGE_GROUP=1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 9791 201 0.981 0.00134 0.978 0.983
## 24 8870 279 0.952 0.00215 0.948 0.956
## 36 7747 282 0.920 0.00279 0.915 0.926
## 48 6595 210 0.893 0.00326 0.887 0.900
## 60 5348 216 0.862 0.00380 0.854 0.869
## 120 1070 504 0.726 0.00695 0.712 0.739
##
## TNM_CLIN_STAGE_GROUP=1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 82128 1263 0.986 0.000400 0.985 0.986
## 24 72641 1639 0.965 0.000638 0.964 0.966
## 36 61084 1654 0.941 0.000848 0.940 0.943
## 48 50407 1480 0.917 0.001042 0.915 0.919
## 60 40560 1201 0.893 0.001225 0.890 0.895
## 120 7811 3257 0.766 0.002532 0.761 0.771
##
## TNM_CLIN_STAGE_GROUP=1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 54788 1190 0.980 0.000579 0.979 0.981
## 24 47096 1807 0.946 0.000969 0.944 0.948
## 36 37773 1718 0.908 0.001290 0.905 0.910
## 48 29886 1417 0.870 0.001576 0.867 0.874
## 60 22806 1149 0.833 0.001857 0.829 0.837
## 120 3361 2356 0.670 0.003792 0.663 0.677
##
## TNM_CLIN_STAGE_GROUP=2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1705 102 0.946 0.00523 0.936 0.956
## 24 1471 142 0.865 0.00807 0.849 0.881
## 36 1244 112 0.796 0.00969 0.778 0.815
## 48 1027 77 0.744 0.01073 0.723 0.765
## 60 847 54 0.702 0.01154 0.680 0.725
## 120 90 117 0.535 0.01850 0.500 0.572
##
## TNM_CLIN_STAGE_GROUP=2A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 19406 813 0.961 0.00133 0.959 0.964
## 24 16245 1384 0.890 0.00223 0.885 0.894
## 36 12639 1262 0.815 0.00288 0.809 0.820
## 48 9653 943 0.748 0.00336 0.742 0.755
## 60 7206 668 0.691 0.00376 0.684 0.699
## 120 1006 1143 0.496 0.00632 0.484 0.509
##
## TNM_CLIN_STAGE_GROUP=2B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 13273 965 0.935 0.00204 0.931 0.939
## 24 10494 1611 0.816 0.00329 0.809 0.822
## 36 7801 1267 0.710 0.00400 0.702 0.718
## 48 5804 800 0.631 0.00443 0.622 0.639
## 60 4177 544 0.565 0.00478 0.556 0.575
## 120 528 841 0.368 0.00712 0.354 0.382
##
## TNM_CLIN_STAGE_GROUP=2C
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6406 1045 0.863 0.00393 0.856 0.871
## 24 4562 1299 0.681 0.00547 0.670 0.691
## 36 3142 831 0.548 0.00605 0.536 0.560
## 48 2173 473 0.457 0.00634 0.445 0.470
## 60 1524 246 0.400 0.00651 0.387 0.413
## 120 148 399 0.220 0.00889 0.203 0.238
##
## TNM_CLIN_STAGE_GROUP=3
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 9131 1454 0.866 0.00327 0.860 0.873
## 24 6869 1523 0.716 0.00443 0.707 0.725
## 36 5137 884 0.617 0.00491 0.608 0.627
## 48 3910 532 0.549 0.00519 0.539 0.559
## 60 2945 283 0.505 0.00539 0.495 0.516
## 120 465 439 0.379 0.00721 0.365 0.393
##
## TNM_CLIN_STAGE_GROUP=4
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4103 8748 0.3321 0.00415 0.3241 0.3403
## 24 2140 1603 0.1967 0.00359 0.1898 0.2039
## 36 1227 547 0.1411 0.00328 0.1348 0.1477
## 48 804 199 0.1159 0.00315 0.1099 0.1223
## 60 559 81 0.1027 0.00312 0.0968 0.1090
## 120 82 130 0.0663 0.00353 0.0598 0.0736
##
## TNM_CLIN_STAGE_GROUP=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1406 113 0.928 0.00655 0.915 0.941
## 24 1275 98 0.862 0.00882 0.845 0.880
## 36 1171 67 0.816 0.00998 0.797 0.836
## 48 1074 61 0.773 0.01088 0.752 0.795
## 60 987 40 0.744 0.01142 0.722 0.766
## 120 400 138 0.619 0.01375 0.593 0.647
##
## TNM_CLIN_STAGE_GROUP=99
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 99043 5937 0.946 0.000687 0.944 0.947
## 24 86876 6115 0.885 0.000985 0.883 0.887
## 36 75066 4926 0.833 0.001176 0.831 0.835
## 48 65153 3668 0.790 0.001309 0.788 0.793
## 60 56039 2862 0.754 0.001416 0.751 0.757
## 120 19360 7703 0.614 0.001893 0.610 0.617
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_CLIN_STAGE_GROUP
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_CLIN_STAGE_GROUP, data = data)
##
## n= 362867, number of events= 89958
## (43 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_CLIN_STAGE_GROUP1 -0.34493 0.70827 0.04577 -7.535 4.86e-14 ***
## TNM_CLIN_STAGE_GROUP1A -0.58497 0.55712 0.04017 -14.561 < 2e-16 ***
## TNM_CLIN_STAGE_GROUP1B -0.18149 0.83403 0.04029 -4.504 6.67e-06 ***
## TNM_CLIN_STAGE_GROUP1C NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUP2 0.43921 1.55148 0.05628 7.805 6.00e-15 ***
## TNM_CLIN_STAGE_GROUP2A 0.46369 1.58992 0.04100 11.310 < 2e-16 ***
## TNM_CLIN_STAGE_GROUP2B 0.88353 2.41942 0.04107 21.513 < 2e-16 ***
## TNM_CLIN_STAGE_GROUP2C 1.38281 3.98610 0.04190 33.004 < 2e-16 ***
## TNM_CLIN_STAGE_GROUP3 1.08099 2.94759 0.04143 26.089 < 2e-16 ***
## TNM_CLIN_STAGE_GROUP3A NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUP3B NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUP3C NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUP4 2.83685 17.06185 0.04021 70.552 < 2e-16 ***
## TNM_CLIN_STAGE_GROUP4A NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUP4B NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUP4C NA NA 0.00000 NA NA
## TNM_CLIN_STAGE_GROUPN_A 0.22022 1.24635 0.05787 3.805 0.000142 ***
## TNM_CLIN_STAGE_GROUP99 0.20140 1.22311 0.03942 5.110 3.23e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_CLIN_STAGE_GROUP1 0.7083 1.41189 0.6475 0.7748
## TNM_CLIN_STAGE_GROUP1A 0.5571 1.79494 0.5149 0.6028
## TNM_CLIN_STAGE_GROUP1B 0.8340 1.19900 0.7707 0.9026
## TNM_CLIN_STAGE_GROUP1C NA NA NA NA
## TNM_CLIN_STAGE_GROUP2 1.5515 0.64454 1.3895 1.7324
## TNM_CLIN_STAGE_GROUP2A 1.5899 0.62896 1.4672 1.7230
## TNM_CLIN_STAGE_GROUP2B 2.4194 0.41332 2.2323 2.6222
## TNM_CLIN_STAGE_GROUP2C 3.9861 0.25087 3.6718 4.3273
## TNM_CLIN_STAGE_GROUP3 2.9476 0.33926 2.7177 3.1969
## TNM_CLIN_STAGE_GROUP3A NA NA NA NA
## TNM_CLIN_STAGE_GROUP3B NA NA NA NA
## TNM_CLIN_STAGE_GROUP3C NA NA NA NA
## TNM_CLIN_STAGE_GROUP4 17.0619 0.05861 15.7689 18.4609
## TNM_CLIN_STAGE_GROUP4A NA NA NA NA
## TNM_CLIN_STAGE_GROUP4B NA NA NA NA
## TNM_CLIN_STAGE_GROUP4C NA NA NA NA
## TNM_CLIN_STAGE_GROUPN_A 1.2464 0.80234 1.1127 1.3960
## TNM_CLIN_STAGE_GROUP99 1.2231 0.81759 1.1322 1.3213
##
## Concordance= 0.705 (se = 0.001 )
## Rsquare= 0.149 (max possible= 0.998 )
## Likelihood ratio test= 58580 on 11 df, p=0
## Wald test = 83674 on 11 df, p=0
## Score (logrank) test = 142755 on 11 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_CLIN_STAGE_GROUP
Pathologic T Stage
uni_var(test_var = "TNM_PATH_T", data_imp = data)
## _________________________________________________
##
## ## TNM_PATH_T
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_T, data = data)
##
## 15174 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_PATH_T=N_A 1608 548 160.3 150.7 NA
## TNM_PATH_T=p0 4729 966 NA 151.8 NA
## TNM_PATH_T=p1 12061 1818 NA 161.4 NA
## TNM_PATH_T=p1A 60788 4622 NA 95.5 NA
## TNM_PATH_T=p1B 23363 2046 97.1 NA NA
## TNM_PATH_T=p2 3707 902 NA 156.0 NA
## TNM_PATH_T=p2A 40964 6867 164.7 164.4 NA
## TNM_PATH_T=p2B 9316 2469 130.2 119.3 133.8
## TNM_PATH_T=p3 2393 906 97.6 87.9 113.3
## TNM_PATH_T=p3A 17370 4845 120.4 116.7 127.2
## TNM_PATH_T=p3B 12918 5054 73.5 70.7 77.7
## TNM_PATH_T=p4 1628 874 45.3 42.2 50.5
## TNM_PATH_T=p4A 9301 3754 69.8 66.8 73.7
## TNM_PATH_T=p4B 15277 8722 34.9 33.9 35.8
## TNM_PATH_T=pIS 1358 221 NA 151.2 NA
## TNM_PATH_T=pX 130955 40263 165.4 164.6 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_T, data = data)
##
## 15174 observations deleted due to missingness
## TNM_PATH_T=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1405 113 0.928 0.00655 0.915 0.941
## 24 1274 98 0.862 0.00883 0.845 0.880
## 36 1170 67 0.816 0.00998 0.797 0.836
## 48 1073 61 0.773 0.01089 0.752 0.794
## 60 986 40 0.743 0.01142 0.721 0.766
## 120 400 138 0.619 0.01375 0.593 0.647
##
## TNM_PATH_T=p0
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3692 425 0.905 0.00439 0.896 0.914
## 24 2872 212 0.849 0.00555 0.838 0.860
## 36 2069 123 0.808 0.00641 0.796 0.821
## 48 1491 75 0.775 0.00721 0.761 0.789
## 60 984 50 0.744 0.00818 0.728 0.760
## 120 106 76 0.616 0.01797 0.582 0.652
##
## TNM_PATH_T=p1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 10570 226 0.980 0.00132 0.977 0.983
## 24 9589 292 0.952 0.00206 0.948 0.956
## 36 8462 272 0.924 0.00262 0.919 0.929
## 48 7173 226 0.897 0.00308 0.891 0.903
## 60 5859 225 0.867 0.00359 0.860 0.874
## 120 1282 509 0.733 0.00672 0.720 0.746
##
## TNM_PATH_T=p1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 50621 847 0.985 0.000525 0.984 0.986
## 24 41969 1022 0.963 0.000839 0.962 0.965
## 36 31134 926 0.939 0.001136 0.937 0.941
## 48 21579 758 0.912 0.001470 0.909 0.915
## 60 13362 542 0.884 0.001871 0.880 0.887
##
## TNM_PATH_T=p1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 19493 383 0.982 0.000912 0.980 0.984
## 24 15895 494 0.955 0.001490 0.952 0.958
## 36 11326 457 0.923 0.002056 0.919 0.927
## 48 7557 319 0.892 0.002628 0.887 0.897
## 60 4426 199 0.863 0.003294 0.856 0.869
##
## TNM_PATH_T=p2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3243 119 0.966 0.00307 0.960 0.972
## 24 2887 162 0.916 0.00481 0.907 0.925
## 36 2540 133 0.872 0.00589 0.861 0.884
## 48 2155 129 0.825 0.00687 0.812 0.839
## 60 1810 95 0.787 0.00761 0.772 0.802
## 120 379 242 0.617 0.01216 0.594 0.641
##
## TNM_PATH_T=p2A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 35584 816 0.979 0.000739 0.977 0.980
## 24 30537 1263 0.942 0.001240 0.940 0.944
## 36 24466 1213 0.901 0.001651 0.898 0.904
## 48 19261 993 0.861 0.002012 0.857 0.865
## 60 14662 774 0.822 0.002357 0.818 0.827
## 120 2789 1619 0.659 0.004441 0.650 0.668
##
## TNM_PATH_T=p2B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7937 385 0.956 0.00221 0.951 0.960
## 24 6614 519 0.890 0.00346 0.883 0.897
## 36 5091 508 0.815 0.00449 0.806 0.824
## 48 3855 357 0.752 0.00525 0.742 0.763
## 60 2830 225 0.703 0.00584 0.692 0.715
## 120 494 426 0.516 0.00968 0.498 0.536
##
## TNM_PATH_T=p3
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2050 149 0.935 0.00518 0.925 0.945
## 24 1754 187 0.847 0.00769 0.832 0.862
## 36 1426 180 0.757 0.00938 0.738 0.775
## 48 1168 118 0.691 0.01035 0.671 0.711
## 60 905 108 0.622 0.01125 0.600 0.644
## 120 170 155 0.453 0.01541 0.424 0.484
##
## TNM_PATH_T=p3A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 15063 643 0.961 0.00152 0.958 0.964
## 24 12546 1081 0.889 0.00254 0.884 0.894
## 36 9650 968 0.814 0.00327 0.807 0.820
## 48 7382 689 0.750 0.00381 0.743 0.758
## 60 5437 515 0.692 0.00430 0.684 0.700
## 120 1026 872 0.502 0.00686 0.489 0.515
##
## TNM_PATH_T=p3B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 11009 866 0.930 0.00231 0.925 0.934
## 24 8564 1397 0.806 0.00368 0.799 0.813
## 36 6167 1106 0.693 0.00448 0.684 0.702
## 48 4485 613 0.617 0.00492 0.608 0.627
## 60 3163 405 0.555 0.00532 0.544 0.565
## 120 512 619 0.369 0.00776 0.354 0.385
##
## TNM_PATH_T=p4
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1274 264 0.833 0.00941 0.814 0.851
## 24 967 218 0.685 0.01193 0.662 0.709
## 36 747 143 0.580 0.01296 0.555 0.606
## 48 556 117 0.484 0.01351 0.458 0.511
## 60 421 59 0.428 0.01378 0.402 0.456
## 120 74 65 0.313 0.01702 0.282 0.348
##
## TNM_PATH_T=p4A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7768 793 0.911 0.00303 0.905 0.917
## 24 5923 1064 0.779 0.00454 0.771 0.788
## 36 4366 706 0.679 0.00531 0.669 0.689
## 48 3217 452 0.602 0.00581 0.591 0.614
## 60 2294 285 0.542 0.00623 0.530 0.555
## 120 399 429 0.374 0.00873 0.357 0.392
##
## TNM_PATH_T=p4B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 11675 2691 0.817 0.00319 0.811 0.824
## 24 7938 2677 0.621 0.00411 0.613 0.629
## 36 5215 1542 0.490 0.00440 0.482 0.499
## 48 3501 788 0.408 0.00454 0.399 0.417
## 60 2366 415 0.354 0.00466 0.345 0.363
## 120 298 578 0.208 0.00610 0.197 0.220
##
## TNM_PATH_T=pIS
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1160 22 0.982 0.00372 0.975 0.990
## 24 990 37 0.949 0.00647 0.937 0.962
## 36 777 42 0.904 0.00921 0.886 0.922
## 48 612 31 0.865 0.01118 0.843 0.887
## 60 459 22 0.829 0.01303 0.804 0.855
## 120 101 64 0.632 0.02541 0.584 0.684
##
## TNM_PATH_T=pX
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 111129 10285 0.919 0.000770 0.917 0.920
## 24 102135 5970 0.868 0.000963 0.867 0.870
## 36 94648 4783 0.827 0.001087 0.825 0.829
## 48 87842 3875 0.793 0.001174 0.791 0.795
## 60 80833 3231 0.763 0.001241 0.761 0.765
## 120 26542 10481 0.634 0.001591 0.631 0.637
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_PATH_T
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_T, data = data)
##
## n= 347736, number of events= 84877
## (15174 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_PATH_Tp0 0.11831 1.12559 0.05353 2.210 0.027086 *
## TNM_PATH_Tp1 -0.61500 0.54064 0.04875 -12.616 < 2e-16 ***
## TNM_PATH_Tp1A -0.90762 0.40348 0.04526 -20.054 < 2e-16 ***
## TNM_PATH_Tp1B -0.73029 0.48177 0.04818 -15.157 < 2e-16 ***
## TNM_PATH_Tp2 -0.13147 0.87680 0.05417 -2.427 0.015228 *
## TNM_PATH_Tp2A -0.36182 0.69641 0.04442 -8.146 3.33e-16 ***
## TNM_PATH_Tp2B 0.17705 1.19368 0.04725 3.747 0.000179 ***
## TNM_PATH_Tp3 0.44268 1.55688 0.05414 8.177 3.33e-16 ***
## TNM_PATH_Tp3A 0.20590 1.22863 0.04510 4.565 4.99e-06 ***
## TNM_PATH_Tp3B 0.65706 1.92910 0.04502 14.595 < 2e-16 ***
## TNM_PATH_Tp4 1.00597 2.73456 0.05452 18.452 < 2e-16 ***
## TNM_PATH_Tp4A 0.70111 2.01599 0.04577 15.317 < 2e-16 ***
## TNM_PATH_Tp4B 1.27041 3.56231 0.04411 28.800 < 2e-16 ***
## TNM_PATH_TpIS -0.37452 0.68762 0.07970 -4.699 2.61e-06 ***
## TNM_PATH_TpX -0.06880 0.93351 0.04301 -1.600 0.109646
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_PATH_Tp0 1.1256 0.8884 1.0135 1.2501
## TNM_PATH_Tp1 0.5406 1.8497 0.4914 0.5948
## TNM_PATH_Tp1A 0.4035 2.4784 0.3692 0.4409
## TNM_PATH_Tp1B 0.4818 2.0757 0.4384 0.5295
## TNM_PATH_Tp2 0.8768 1.1405 0.7885 0.9750
## TNM_PATH_Tp2A 0.6964 1.4359 0.6383 0.7598
## TNM_PATH_Tp2B 1.1937 0.8377 1.0881 1.3095
## TNM_PATH_Tp3 1.5569 0.6423 1.4001 1.7311
## TNM_PATH_Tp3A 1.2286 0.8139 1.1247 1.3422
## TNM_PATH_Tp3B 1.9291 0.5184 1.7662 2.1071
## TNM_PATH_Tp4 2.7346 0.3657 2.4574 3.0429
## TNM_PATH_Tp4A 2.0160 0.4960 1.8430 2.2052
## TNM_PATH_Tp4B 3.5623 0.2807 3.2673 3.8840
## TNM_PATH_TpIS 0.6876 1.4543 0.5882 0.8039
## TNM_PATH_TpX 0.9335 1.0712 0.8580 1.0156
##
## Concordance= 0.641 (se = 0.001 )
## Rsquare= 0.063 (max possible= 0.997 )
## Likelihood ratio test= 22560 on 15 df, p=0
## Wald test = 25245 on 15 df, p=0
## Score (logrank) test = 29762 on 15 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_PATH_T
Pathologic N Stage
uni_var(test_var = "TNM_PATH_N", data_imp = data)
## _________________________________________________
##
## ## TNM_PATH_N
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_N, data = data)
##
## 28869 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_PATH_N=N_A 1608 548 160.3 150.7 NA
## TNM_PATH_N=p0 161766 28438 NA 165.4 NA
## TNM_PATH_N=p1 4601 1864 85.2 76.4 94.5
## TNM_PATH_N=p1A 10736 2992 134.1 127.5 148.5
## TNM_PATH_N=p1B 2516 1177 49.1 43.1 55.5
## TNM_PATH_N=p2 1370 679 50.8 45.8 59.0
## TNM_PATH_N=p2A 3523 1289 79.7 73.7 91.1
## TNM_PATH_N=p2B 1858 913 41.5 37.5 47.4
## TNM_PATH_N=p2C 1798 860 48.8 43.7 54.3
## TNM_PATH_N=p3 4889 3056 25.0 23.9 26.2
## TNM_PATH_N=pX 139376 41237 161.3 159.6 164.5
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_N, data = data)
##
## 28869 observations deleted due to missingness
## TNM_PATH_N=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1405 113 0.928 0.00655 0.915 0.941
## 24 1274 98 0.862 0.00883 0.845 0.880
## 36 1170 67 0.816 0.00998 0.797 0.836
## 48 1073 61 0.773 0.01089 0.752 0.794
## 60 986 40 0.743 0.01142 0.721 0.766
## 120 400 138 0.619 0.01375 0.593 0.647
##
## TNM_PATH_N=p0
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 139818 3568 0.976 0.000392 0.976 0.977
## 24 121377 5311 0.937 0.000645 0.936 0.939
## 36 99735 5080 0.895 0.000846 0.893 0.897
## 48 80892 3840 0.858 0.001004 0.856 0.860
## 60 63553 3057 0.822 0.001152 0.820 0.824
## 120 13706 6754 0.674 0.002023 0.670 0.677
##
## TNM_PATH_N=p1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3778 490 0.889 0.00474 0.880 0.898
## 24 3001 479 0.772 0.00647 0.759 0.784
## 36 2337 353 0.676 0.00741 0.662 0.691
## 48 1832 210 0.612 0.00793 0.596 0.627
## 60 1380 128 0.564 0.00837 0.548 0.580
## 120 247 183 0.437 0.01134 0.415 0.459
##
## TNM_PATH_N=p1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 9435 407 0.960 0.00194 0.956 0.964
## 24 7696 796 0.875 0.00338 0.868 0.882
## 36 5840 632 0.797 0.00429 0.788 0.805
## 48 4401 437 0.731 0.00495 0.722 0.741
## 60 3208 279 0.680 0.00549 0.669 0.691
## 120 595 405 0.529 0.00857 0.512 0.546
##
## TNM_PATH_N=p1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1945 381 0.842 0.00746 0.827 0.856
## 24 1400 365 0.676 0.00982 0.657 0.696
## 36 968 216 0.563 0.01079 0.542 0.585
## 48 692 92 0.504 0.01131 0.482 0.526
## 60 490 52 0.461 0.01181 0.438 0.485
## 120 85 65 0.354 0.01574 0.324 0.386
##
## TNM_PATH_N=p2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1121 168 0.873 0.00915 0.855 0.891
## 24 834 199 0.712 0.01274 0.688 0.738
## 36 635 121 0.604 0.01411 0.577 0.632
## 48 475 90 0.514 0.01489 0.485 0.544
## 60 366 43 0.463 0.01529 0.434 0.494
## 120 75 48 0.364 0.01879 0.329 0.402
##
## TNM_PATH_N=p2A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3059 188 0.944 0.00398 0.936 0.952
## 24 2377 392 0.817 0.00690 0.804 0.831
## 36 1700 293 0.707 0.00846 0.691 0.724
## 48 1247 166 0.632 0.00936 0.614 0.651
## 60 890 95 0.579 0.01007 0.559 0.599
## 120 162 149 0.413 0.01495 0.385 0.444
##
## TNM_PATH_N=p2B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1442 287 0.840 0.00867 0.823 0.857
## 24 991 305 0.653 0.01161 0.631 0.677
## 36 668 165 0.535 0.01268 0.511 0.560
## 48 463 74 0.469 0.01325 0.444 0.496
## 60 320 33 0.430 0.01377 0.404 0.458
## 120 61 43 0.329 0.01833 0.295 0.367
##
## TNM_PATH_N=p2C
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1427 227 0.868 0.00817 0.852 0.884
## 24 1004 275 0.692 0.01151 0.670 0.715
## 36 693 144 0.583 0.01281 0.559 0.609
## 48 479 87 0.503 0.01367 0.477 0.530
## 60 337 51 0.443 0.01438 0.416 0.473
## 120 58 73 0.287 0.01891 0.253 0.327
##
## TNM_PATH_N=p3
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3417 1294 0.730 0.00643 0.717 0.742
## 24 2133 970 0.513 0.00740 0.498 0.527
## 36 1404 407 0.407 0.00752 0.393 0.422
## 48 930 191 0.345 0.00761 0.330 0.360
## 60 656 81 0.311 0.00774 0.297 0.327
## 120 100 102 0.231 0.00959 0.213 0.250
##
## TNM_PATH_N=pX
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 115671 11418 0.914 0.000766 0.913 0.916
## 24 101946 6977 0.858 0.000975 0.856 0.860
## 36 88685 5346 0.811 0.001113 0.809 0.813
## 48 77042 4131 0.771 0.001217 0.769 0.774
## 60 66676 3203 0.738 0.001301 0.735 0.740
## 120 19083 8917 0.600 0.001758 0.596 0.603
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_PATH_N
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_N, data = data)
##
## n= 334041, number of events= 83053
## (28869 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_PATH_Np0 -0.35771 0.69927 0.04315 -8.290 < 2e-16 ***
## TNM_PATH_Np1 0.63924 1.89504 0.04862 13.147 < 2e-16 ***
## TNM_PATH_Np1A 0.22139 1.24781 0.04650 4.761 1.92e-06 ***
## TNM_PATH_Np1B 0.98521 2.67836 0.05176 19.034 < 2e-16 ***
## TNM_PATH_Np2 0.89237 2.44091 0.05745 15.533 < 2e-16 ***
## TNM_PATH_Np2A 0.57084 1.76975 0.05103 11.186 < 2e-16 ***
## TNM_PATH_Np2B 1.06589 2.90343 0.05409 19.708 < 2e-16 ***
## TNM_PATH_Np2C 1.00466 2.73098 0.05470 18.365 < 2e-16 ***
## TNM_PATH_Np3 1.46776 4.33951 0.04646 31.591 < 2e-16 ***
## TNM_PATH_NpX 0.05819 1.05991 0.04301 1.353 0.176
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_PATH_Np0 0.6993 1.4301 0.6426 0.761
## TNM_PATH_Np1 1.8950 0.5277 1.7228 2.085
## TNM_PATH_Np1A 1.2478 0.8014 1.1391 1.367
## TNM_PATH_Np1B 2.6784 0.3734 2.4200 2.964
## TNM_PATH_Np2 2.4409 0.4097 2.1810 2.732
## TNM_PATH_Np2A 1.7698 0.5651 1.6013 1.956
## TNM_PATH_Np2B 2.9034 0.3444 2.6114 3.228
## TNM_PATH_Np2C 2.7310 0.3662 2.4533 3.040
## TNM_PATH_Np3 4.3395 0.2304 3.9618 4.753
## TNM_PATH_NpX 1.0599 0.9435 0.9742 1.153
##
## Concordance= 0.604 (se = 0.001 )
## Rsquare= 0.036 (max possible= 0.998 )
## Likelihood ratio test= 12120 on 10 df, p=0
## Wald test = 15069 on 10 df, p=0
## Score (logrank) test = 17350 on 10 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_PATH_N
Pathologic M Stage
uni_var(test_var = "TNM_PATH_M", data_imp = data)
## _________________________________________________
##
## ## TNM_PATH_M
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_M, data = data)
##
## 199448 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_PATH_M=N_A 1609 549 160.33 150.70 NA
## TNM_PATH_M=p1 1989 1731 7.43 6.97 8.08
## TNM_PATH_M=p1A 1165 718 23.13 20.50 26.41
## TNM_PATH_M=p1B 907 704 10.55 9.43 12.12
## TNM_PATH_M=p1C 2241 1898 5.88 5.49 6.34
## TNM_PATH_M=pX 155551 49114 165.19 164.47 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_M, data = data)
##
## 199448 observations deleted due to missingness
## TNM_PATH_M=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1406 113 0.928 0.00655 0.915 0.941
## 24 1275 98 0.862 0.00882 0.845 0.880
## 36 1171 67 0.816 0.00998 0.797 0.836
## 48 1074 61 0.773 0.01088 0.752 0.795
## 60 986 41 0.743 0.01143 0.721 0.766
## 120 400 138 0.619 0.01375 0.592 0.646
##
## TNM_PATH_M=p1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 669 1261 0.3534 0.01087 0.3327 0.3753
## 24 379 265 0.2105 0.00938 0.1929 0.2297
## 36 260 98 0.1546 0.00842 0.1389 0.1720
## 48 205 39 0.1305 0.00795 0.1158 0.1470
## 60 172 20 0.1173 0.00767 0.1032 0.1334
## 120 43 41 0.0833 0.00725 0.0702 0.0988
##
## TNM_PATH_M=p1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 711 362 0.675 0.0141 0.647 0.703
## 24 466 184 0.492 0.0154 0.463 0.523
## 36 315 89 0.389 0.0156 0.360 0.421
## 48 239 33 0.345 0.0156 0.316 0.377
## 60 191 13 0.325 0.0157 0.295 0.357
## 120 39 34 0.231 0.0187 0.197 0.271
##
## TNM_PATH_M=p1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 396 468 0.470 0.0169 0.4376 0.504
## 24 215 138 0.299 0.0159 0.2691 0.331
## 36 107 59 0.206 0.0149 0.1788 0.237
## 48 65 20 0.163 0.0146 0.1364 0.194
## 60 41 10 0.134 0.0146 0.1087 0.166
## 120 7 7 0.102 0.0155 0.0759 0.138
##
## TNM_PATH_M=p1C
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 610 1536 0.2964 0.00986 0.2777 0.3164
## 24 289 246 0.1695 0.00836 0.1539 0.1867
## 36 154 71 0.1217 0.00773 0.1075 0.1379
## 48 96 21 0.1036 0.00753 0.0899 0.1195
## 60 59 13 0.0880 0.00756 0.0743 0.1041
## 120 4 11 0.0607 0.00900 0.0454 0.0811
##
## TNM_PATH_M=pX
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 137506 7936 0.947 0.000578 0.946 0.948
## 24 126905 7769 0.893 0.000808 0.891 0.895
## 36 117977 6697 0.845 0.000951 0.844 0.847
## 48 110012 5434 0.806 0.001046 0.804 0.808
## 60 101841 4589 0.772 0.001117 0.770 0.774
## 120 34079 14529 0.631 0.001437 0.628 0.634
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_PATH_M
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_M, data = data)
##
## n= 163462, number of events= 54714
## (199448 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_PATH_Mp1 2.28750 9.85031 0.04910 46.590 <2e-16 ***
## TNM_PATH_Mp1A 1.44157 4.22733 0.05676 25.400 <2e-16 ***
## TNM_PATH_Mp1B 2.18953 8.93099 0.05710 38.346 <2e-16 ***
## TNM_PATH_Mp1C 2.64046 14.01966 0.04874 54.173 <2e-16 ***
## TNM_PATH_MpX -0.09322 0.91099 0.04292 -2.172 0.0298 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_PATH_Mp1 9.850 0.10152 8.9466 10.8453
## TNM_PATH_Mp1A 4.227 0.23656 3.7823 4.7247
## TNM_PATH_Mp1B 8.931 0.11197 7.9854 9.9885
## TNM_PATH_Mp1C 14.020 0.07133 12.7423 15.4250
## TNM_PATH_MpX 0.911 1.09771 0.8375 0.9909
##
## Concordance= 0.554 (se = 0 )
## Rsquare= 0.083 (max possible= 1 )
## Likelihood ratio test= 14212 on 5 df, p=0
## Wald test = 24732 on 5 df, p=0
## Score (logrank) test = 40425 on 5 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_PATH_M
Pathologic Stage Group
uni_var(test_var = "TNM_PATH_STAGE_GROUP", data_imp = data)
## _________________________________________________
##
## ## TNM_PATH_STAGE_GROUP
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_STAGE_GROUP, data = data)
##
## 11146 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## TNM_PATH_STAGE_GROUP=0 2692 446 NA 148.21 NA
## TNM_PATH_STAGE_GROUP=1 8007 1254 NA NA NA
## TNM_PATH_STAGE_GROUP=1A 86795 10430 NA NA NA
## TNM_PATH_STAGE_GROUP=1B 70294 10651 NA NA NA
## TNM_PATH_STAGE_GROUP=2 1642 519 150.54 129.41 NA
## TNM_PATH_STAGE_GROUP=2A 24145 6449 135.36 132.04 142.42
## TNM_PATH_STAGE_GROUP=2B 16599 6174 89.26 86.54 92.39
## TNM_PATH_STAGE_GROUP=2C 8258 4301 47.90 46.59 49.71
## TNM_PATH_STAGE_GROUP=3 6964 3123 82.40 76.25 88.18
## TNM_PATH_STAGE_GROUP=3A 10302 2803 154.78 139.93 NA
## TNM_PATH_STAGE_GROUP=3B 9390 3943 67.78 64.76 71.85
## TNM_PATH_STAGE_GROUP=3C 6606 3825 31.38 29.96 32.59
## TNM_PATH_STAGE_GROUP=4 7652 6190 8.51 8.08 8.87
## TNM_PATH_STAGE_GROUP=N_A 1609 548 160.33 150.70 NA
## TNM_PATH_STAGE_GROUP=99 90809 26192 160.03 155.70 161.68
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_STAGE_GROUP, data = data)
##
## 11146 observations deleted due to missingness
## TNM_PATH_STAGE_GROUP=0
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2302 55 0.978 0.00293 0.972 0.984
## 24 1970 76 0.944 0.00477 0.935 0.953
## 36 1548 71 0.906 0.00640 0.893 0.918
## 48 1255 51 0.874 0.00759 0.859 0.889
## 60 963 46 0.838 0.00893 0.821 0.856
## 120 229 132 0.649 0.01718 0.616 0.683
##
## TNM_PATH_STAGE_GROUP=1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7088 124 0.984 0.00147 0.981 0.986
## 24 6501 163 0.960 0.00231 0.956 0.965
## 36 5753 179 0.932 0.00303 0.927 0.938
## 48 4996 155 0.906 0.00362 0.899 0.913
## 60 4158 153 0.876 0.00423 0.868 0.884
## 120 1208 414 0.743 0.00733 0.728 0.757
##
## TNM_PATH_STAGE_GROUP=1A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 75125 1076 0.987 0.000405 0.986 0.987
## 24 67214 1425 0.967 0.000649 0.966 0.968
## 36 57766 1448 0.945 0.000857 0.943 0.947
## 48 48907 1333 0.921 0.001049 0.919 0.924
## 60 40676 1125 0.899 0.001226 0.896 0.901
## 120 10493 3459 0.775 0.002349 0.771 0.780
##
## TNM_PATH_STAGE_GROUP=1B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 61234 1018 0.984 0.000483 0.984 0.985
## 24 53754 1595 0.957 0.000816 0.956 0.959
## 36 44573 1750 0.924 0.001116 0.922 0.926
## 48 36505 1459 0.891 0.001368 0.888 0.894
## 60 29141 1277 0.857 0.001617 0.854 0.860
## 120 6648 3134 0.705 0.002983 0.699 0.711
##
## TNM_PATH_STAGE_GROUP=2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1459 53 0.966 0.00459 0.957 0.975
## 24 1299 97 0.900 0.00774 0.885 0.915
## 36 1128 95 0.833 0.00979 0.814 0.852
## 48 992 60 0.787 0.01090 0.766 0.808
## 60 835 66 0.731 0.01207 0.708 0.755
## 120 194 138 0.552 0.01709 0.519 0.586
##
## TNM_PATH_STAGE_GROUP=2A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 21108 658 0.971 0.00112 0.969 0.973
## 24 18179 1178 0.915 0.00191 0.911 0.918
## 36 14677 1219 0.849 0.00254 0.844 0.854
## 48 11757 938 0.790 0.00300 0.784 0.796
## 60 9236 743 0.736 0.00339 0.729 0.743
## 120 1941 1556 0.541 0.00527 0.530 0.551
##
## TNM_PATH_STAGE_GROUP=2B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 14411 818 0.948 0.00176 0.945 0.952
## 24 11762 1445 0.849 0.00294 0.843 0.855
## 36 8989 1310 0.748 0.00369 0.740 0.755
## 48 6954 833 0.673 0.00413 0.665 0.681
## 60 5273 570 0.613 0.00447 0.604 0.622
## 120 1011 1093 0.416 0.00621 0.404 0.428
##
## TNM_PATH_STAGE_GROUP=2C
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6869 843 0.893 0.00347 0.887 0.900
## 24 5068 1242 0.725 0.00515 0.715 0.735
## 36 3608 843 0.596 0.00586 0.585 0.608
## 48 2546 541 0.499 0.00623 0.487 0.511
## 60 1855 297 0.435 0.00644 0.423 0.448
## 120 278 505 0.250 0.00800 0.235 0.266
##
## TNM_PATH_STAGE_GROUP=3
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5915 618 0.908 0.00354 0.901 0.915
## 24 4706 884 0.768 0.00526 0.758 0.778
## 36 3784 567 0.672 0.00596 0.660 0.684
## 48 3104 348 0.607 0.00631 0.595 0.620
## 60 2561 223 0.561 0.00655 0.548 0.574
## 120 603 431 0.427 0.00788 0.412 0.443
##
## TNM_PATH_STAGE_GROUP=3A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 9201 286 0.971 0.00170 0.968 0.974
## 24 7665 693 0.894 0.00321 0.888 0.901
## 36 6013 586 0.821 0.00415 0.812 0.829
## 48 4701 442 0.756 0.00484 0.746 0.765
## 60 3593 289 0.705 0.00537 0.694 0.715
## 120 754 466 0.554 0.00804 0.539 0.570
##
## TNM_PATH_STAGE_GROUP=3B
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7993 705 0.921 0.00285 0.916 0.927
## 24 6101 1172 0.780 0.00450 0.771 0.789
## 36 4439 817 0.668 0.00531 0.657 0.678
## 48 3308 461 0.593 0.00575 0.581 0.604
## 60 2367 308 0.532 0.00613 0.520 0.544
## 120 484 447 0.372 0.00817 0.357 0.389
##
## TNM_PATH_STAGE_GROUP=3C
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5036 1266 0.803 0.00496 0.793 0.813
## 24 3296 1284 0.589 0.00630 0.577 0.601
## 36 2166 656 0.462 0.00662 0.450 0.476
## 48 1438 319 0.387 0.00677 0.373 0.400
## 60 1014 124 0.349 0.00690 0.336 0.363
## 120 166 162 0.253 0.00876 0.237 0.271
##
## TNM_PATH_STAGE_GROUP=4
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2857 4448 0.4024 0.00572 0.391 0.414
## 24 1592 1019 0.2529 0.00518 0.243 0.263
## 36 969 385 0.1862 0.00481 0.177 0.196
## 48 673 155 0.1539 0.00463 0.145 0.163
## 60 489 66 0.1375 0.00456 0.129 0.147
## 120 100 104 0.0952 0.00496 0.086 0.105
##
## TNM_PATH_STAGE_GROUP=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1406 113 0.928 0.00655 0.915 0.941
## 24 1275 98 0.862 0.00882 0.845 0.880
## 36 1171 67 0.816 0.00998 0.797 0.836
## 48 1074 61 0.773 0.01088 0.752 0.795
## 60 987 40 0.744 0.01142 0.722 0.766
## 120 400 138 0.619 0.01375 0.593 0.647
##
## TNM_PATH_STAGE_GROUP=99
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 73796 8329 0.904 0.00100 0.902 0.906
## 24 63760 4646 0.845 0.00126 0.842 0.847
## 36 54124 3300 0.799 0.00142 0.796 0.801
## 48 45892 2533 0.759 0.00156 0.756 0.762
## 60 38530 1890 0.726 0.00167 0.722 0.729
## 120 10063 4840 0.590 0.00232 0.586 0.595
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: TNM_PATH_STAGE_GROUP
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ TNM_PATH_STAGE_GROUP, data = data)
##
## n= 351764, number of events= 86848
## (11146 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## TNM_PATH_STAGE_GROUP1 -0.27207 0.76180 0.05514 -4.934 8.04e-07 ***
## TNM_PATH_STAGE_GROUP1A -0.46113 0.63057 0.04836 -9.536 < 2e-16 ***
## TNM_PATH_STAGE_GROUP1B -0.15970 0.85240 0.04833 -3.304 0.000953 ***
## TNM_PATH_STAGE_GROUP1C NA NA 0.00000 NA NA
## TNM_PATH_STAGE_GROUP2 0.46330 1.58930 0.06457 7.175 7.22e-13 ***
## TNM_PATH_STAGE_GROUP2A 0.45204 1.57152 0.04896 9.233 < 2e-16 ***
## TNM_PATH_STAGE_GROUP2B 0.87922 2.40902 0.04903 17.931 < 2e-16 ***
## TNM_PATH_STAGE_GROUP2C 1.39818 4.04783 0.04975 28.103 < 2e-16 ***
## TNM_PATH_STAGE_GROUP3 1.00907 2.74306 0.05062 19.934 < 2e-16 ***
## TNM_PATH_STAGE_GROUP3A 0.50918 1.66393 0.05098 9.988 < 2e-16 ***
## TNM_PATH_STAGE_GROUP3B 1.10511 3.01956 0.04996 22.119 < 2e-16 ***
## TNM_PATH_STAGE_GROUP3C 1.69328 5.43730 0.05005 33.831 < 2e-16 ***
## TNM_PATH_STAGE_GROUP4 2.69749 14.84243 0.04907 54.971 < 2e-16 ***
## TNM_PATH_STAGE_GROUP4A NA NA 0.00000 NA NA
## TNM_PATH_STAGE_GROUP4B NA NA 0.00000 NA NA
## TNM_PATH_STAGE_GROUP4C NA NA 0.00000 NA NA
## TNM_PATH_STAGE_GROUPN_A 0.36782 1.44458 0.06379 5.766 8.10e-09 ***
## TNM_PATH_STAGE_GROUP99 0.49614 1.64238 0.04775 10.389 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## TNM_PATH_STAGE_GROUP1 0.7618 1.31268 0.6838 0.8487
## TNM_PATH_STAGE_GROUP1A 0.6306 1.58587 0.5736 0.6933
## TNM_PATH_STAGE_GROUP1B 0.8524 1.17316 0.7754 0.9371
## TNM_PATH_STAGE_GROUP1C NA NA NA NA
## TNM_PATH_STAGE_GROUP2 1.5893 0.62921 1.4004 1.8037
## TNM_PATH_STAGE_GROUP2A 1.5715 0.63633 1.4277 1.7298
## TNM_PATH_STAGE_GROUP2B 2.4090 0.41511 2.1883 2.6520
## TNM_PATH_STAGE_GROUP2C 4.0478 0.24705 3.6717 4.4624
## TNM_PATH_STAGE_GROUP3 2.7431 0.36456 2.4840 3.0292
## TNM_PATH_STAGE_GROUP3A 1.6639 0.60099 1.5057 1.8388
## TNM_PATH_STAGE_GROUP3B 3.0196 0.33117 2.7379 3.3302
## TNM_PATH_STAGE_GROUP3C 5.4373 0.18391 4.9292 5.9977
## TNM_PATH_STAGE_GROUP4 14.8424 0.06737 13.4814 16.3408
## TNM_PATH_STAGE_GROUP4A NA NA NA NA
## TNM_PATH_STAGE_GROUP4B NA NA NA NA
## TNM_PATH_STAGE_GROUP4C NA NA NA NA
## TNM_PATH_STAGE_GROUPN_A 1.4446 0.69224 1.2748 1.6370
## TNM_PATH_STAGE_GROUP99 1.6424 0.60887 1.4956 1.8035
##
## Concordance= 0.698 (se = 0.001 )
## Rsquare= 0.116 (max possible= 0.998 )
## Likelihood ratio test= 43484 on 14 df, p=0
## Wald test = 54341 on 14 df, p=0
## Score (logrank) test = 78834 on 14 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: TNM_PATH_STAGE_GROUP
Margins
uni_var(test_var = "MARGINS", data_imp = data)
## _________________________________________________
##
## ## MARGINS
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ MARGINS, data = data)
##
## n events median 0.95LCL 0.95UCL
## MARGINS=No Residual 329265 70369 NA 164.73 NA
## MARGINS=Residual, NOS 5326 2401 74.12 68.83 80.5
## MARGINS=Microscopic Resid 5723 2641 68.11 64.89 73.4
## MARGINS=Macroscopic Resid 366 242 23.06 19.25 27.8
## MARGINS=Not evaluable 999 433 82.40 73.66 104.2
## MARGINS=No surg 16733 12252 8.87 8.57 9.2
## MARGINS=Unknown 4498 1634 139.24 129.31 149.4
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ MARGINS, data = data)
##
## MARGINS=No Residual
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 284582 10282 0.967 0.000324 0.966 0.967
## 24 246304 14276 0.916 0.000514 0.915 0.917
## 36 204546 11986 0.868 0.000646 0.867 0.870
## 48 168935 8929 0.828 0.000746 0.826 0.829
## 60 136867 6838 0.791 0.000833 0.790 0.793
## 120 32872 15998 0.646 0.001316 0.643 0.648
##
## MARGINS=Residual, NOS
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3980 929 0.818 0.00541 0.807 0.829
## 24 3200 494 0.713 0.00647 0.700 0.725
## 36 2576 316 0.638 0.00702 0.625 0.652
## 48 2032 241 0.575 0.00742 0.561 0.590
## 60 1659 114 0.541 0.00764 0.526 0.556
## 120 346 280 0.399 0.00973 0.381 0.419
##
## MARGINS=Microscopic Resid
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4455 863 0.843 0.00492 0.833 0.853
## 24 3552 597 0.726 0.00615 0.714 0.738
## 36 2817 383 0.643 0.00674 0.630 0.657
## 48 2240 268 0.579 0.00713 0.565 0.593
## 60 1808 168 0.532 0.00740 0.518 0.547
## 120 334 324 0.374 0.00983 0.355 0.394
##
## MARGINS=Macroscopic Resid
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 229 120 0.663 0.0251 0.615 0.714
## 24 149 60 0.481 0.0271 0.431 0.538
## 36 107 25 0.397 0.0271 0.348 0.454
## 48 79 17 0.331 0.0270 0.282 0.388
## 60 63 3 0.317 0.0270 0.268 0.375
## 120 9 14 0.192 0.0330 0.137 0.269
##
## MARGINS=Not evaluable
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 764 162 0.830 0.0122 0.806 0.854
## 24 603 107 0.709 0.0150 0.681 0.739
## 36 499 51 0.646 0.0161 0.616 0.679
## 48 416 25 0.612 0.0166 0.580 0.646
## 60 332 26 0.570 0.0174 0.537 0.605
## 120 82 57 0.430 0.0216 0.390 0.475
##
## MARGINS=No surg
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6526 9055 0.435 0.00394 0.428 0.443
## 24 4167 1743 0.314 0.00377 0.306 0.321
## 36 2879 674 0.259 0.00366 0.252 0.266
## 48 2112 329 0.226 0.00361 0.219 0.234
## 60 1593 168 0.207 0.00361 0.200 0.214
## 120 340 255 0.157 0.00402 0.149 0.165
##
## MARGINS=Unknown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3621 536 0.875 0.00504 0.866 0.885
## 24 3084 346 0.789 0.00632 0.777 0.802
## 36 2655 216 0.732 0.00697 0.718 0.746
## 48 2320 140 0.692 0.00737 0.677 0.706
## 60 1980 93 0.662 0.00767 0.647 0.677
## 120 589 261 0.536 0.00970 0.517 0.555
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: MARGINS
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ MARGINS, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## MARGINSResidual, NOS 0.967379 2.631040 0.020756 46.61 <2e-16 ***
## MARGINSMicroscopic Resid 0.985189 2.678317 0.019826 49.69 <2e-16 ***
## MARGINSMacroscopic Resid 1.732810 5.656527 0.064404 26.91 <2e-16 ***
## MARGINSNot evaluable 0.873543 2.395383 0.048205 18.12 <2e-16 ***
## MARGINSNo surg 2.251671 9.503601 0.009911 227.19 <2e-16 ***
## MARGINSUnknown 0.520778 1.683337 0.025027 20.81 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## MARGINSResidual, NOS 2.631 0.3801 2.526 2.740
## MARGINSMicroscopic Resid 2.678 0.3734 2.576 2.784
## MARGINSMacroscopic Resid 5.657 0.1768 4.986 6.418
## MARGINSNot evaluable 2.395 0.4175 2.179 2.633
## MARGINSNo surg 9.504 0.1052 9.321 9.690
## MARGINSUnknown 1.683 0.5941 1.603 1.768
##
## Concordance= 0.612 (se = 0 )
## Rsquare= 0.091 (max possible= 0.998 )
## Likelihood ratio test= 34649 on 6 df, p=0
## Wald test = 54125 on 6 df, p=0
## Score (logrank) test = 78275 on 6 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: MARGINS
Margins Yes/No
#uni_var(test_var = "MARGINS_YN", data_imp = data)
30 Day Readmission
uni_var(test_var = "READM_HOSP_30_DAYS_F", data_imp = data)
## _________________________________________________
##
## ## READM_HOSP_30_DAYS_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ READM_HOSP_30_DAYS_F, data = data)
##
## n events median 0.95LCL
## READM_HOSP_30_DAYS_F=No_Surg_or_No_Readmit 347736 84921 164 162
## READM_HOSP_30_DAYS_F=Unplan_Readmit_Same 3407 1253 113 103
## READM_HOSP_30_DAYS_F=Plan_Readmit_Same 5388 1646 157 140
## READM_HOSP_30_DAYS_F=PlanUnplan_Same 515 135 130 122
## READM_HOSP_30_DAYS_F=9 5864 2017 160 158
## 0.95UCL
## READM_HOSP_30_DAYS_F=No_Surg_or_No_Readmit 165
## READM_HOSP_30_DAYS_F=Unplan_Readmit_Same 124
## READM_HOSP_30_DAYS_F=Plan_Readmit_Same NA
## READM_HOSP_30_DAYS_F=PlanUnplan_Same NA
## READM_HOSP_30_DAYS_F=9 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ READM_HOSP_30_DAYS_F, data = data)
##
## READM_HOSP_30_DAYS_F=No_Surg_or_No_Readmit
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 291361 20768 0.937 0.000424 0.936 0.938
## 24 249996 16607 0.881 0.000579 0.880 0.882
## 36 206568 12940 0.833 0.000687 0.831 0.834
## 48 169989 9385 0.792 0.000771 0.790 0.794
## 60 137365 7017 0.757 0.000845 0.755 0.758
## 120 32483 16133 0.616 0.001285 0.613 0.618
##
## READM_HOSP_30_DAYS_F=Unplan_Readmit_Same
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2713 385 0.882 0.00567 0.871 0.893
## 24 2245 264 0.793 0.00728 0.779 0.807
## 36 1869 156 0.735 0.00810 0.719 0.751
## 48 1536 133 0.679 0.00880 0.662 0.697
## 60 1236 87 0.638 0.00932 0.620 0.657
## 120 303 202 0.484 0.01245 0.460 0.509
##
## READM_HOSP_30_DAYS_F=Plan_Readmit_Same
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4635 280 0.945 0.00320 0.939 0.951
## 24 3988 361 0.869 0.00482 0.860 0.879
## 36 3370 264 0.809 0.00574 0.798 0.820
## 48 2819 195 0.760 0.00639 0.747 0.772
## 60 2327 148 0.717 0.00693 0.703 0.731
## 120 702 348 0.566 0.00934 0.548 0.585
##
## READM_HOSP_30_DAYS_F=PlanUnplan_Same
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 450 30 0.939 0.0107 0.918 0.961
## 24 399 20 0.896 0.0139 0.869 0.924
## 36 315 24 0.837 0.0175 0.803 0.872
## 48 261 20 0.781 0.0203 0.742 0.822
## 60 217 10 0.750 0.0217 0.709 0.794
## 120 24 29 0.573 0.0388 0.502 0.654
##
## READM_HOSP_30_DAYS_F=9
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4998 484 0.914 0.00373 0.907 0.922
## 24 4431 371 0.845 0.00488 0.836 0.855
## 36 3957 267 0.793 0.00553 0.782 0.804
## 48 3529 216 0.748 0.00599 0.737 0.760
## 60 3157 148 0.716 0.00629 0.704 0.728
## 120 1060 477 0.578 0.00779 0.563 0.593
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: READM_HOSP_30_DAYS_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ READM_HOSP_30_DAYS_F, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z
## READM_HOSP_30_DAYS_FUnplan_Readmit_Same 0.47735 1.61180 0.02846 16.774
## READM_HOSP_30_DAYS_FPlan_Readmit_Same 0.14940 1.16114 0.02489 6.003
## READM_HOSP_30_DAYS_FPlanUnplan_Same 0.07259 1.07529 0.08614 0.843
## READM_HOSP_30_DAYS_F9 0.14804 1.15956 0.02254 6.567
## Pr(>|z|)
## READM_HOSP_30_DAYS_FUnplan_Readmit_Same < 2e-16 ***
## READM_HOSP_30_DAYS_FPlan_Readmit_Same 1.94e-09 ***
## READM_HOSP_30_DAYS_FPlanUnplan_Same 0.399
## READM_HOSP_30_DAYS_F9 5.13e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95
## READM_HOSP_30_DAYS_FUnplan_Readmit_Same 1.612 0.6204 1.5244
## READM_HOSP_30_DAYS_FPlan_Readmit_Same 1.161 0.8612 1.1059
## READM_HOSP_30_DAYS_FPlanUnplan_Same 1.075 0.9300 0.9083
## READM_HOSP_30_DAYS_F9 1.160 0.8624 1.1094
## upper .95
## READM_HOSP_30_DAYS_FUnplan_Readmit_Same 1.704
## READM_HOSP_30_DAYS_FPlan_Readmit_Same 1.219
## READM_HOSP_30_DAYS_FPlanUnplan_Same 1.273
## READM_HOSP_30_DAYS_F9 1.212
##
## Concordance= 0.506 (se = 0 )
## Rsquare= 0.001 (max possible= 0.998 )
## Likelihood ratio test= 311.7 on 4 df, p=0
## Wald test = 352.3 on 4 df, p=0
## Score (logrank) test = 357.7 on 4 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: READM_HOSP_30_DAYS_F
Radiation Type
uni_var(test_var = "RX_SUMM_RADIATION_F", data_imp = data)
## _________________________________________________
##
## ## RX_SUMM_RADIATION_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RX_SUMM_RADIATION_F, data = data)
##
## n events median 0.95LCL
## RX_SUMM_RADIATION_F=None 349080 81074 164.7 164.5
## RX_SUMM_RADIATION_F=Beam Radiation 11458 8190 15.5 14.9
## RX_SUMM_RADIATION_F=Radioactive Implants 44 20 64.3 33.7
## RX_SUMM_RADIATION_F=Radioisotopes 9 5 95.3 39.0
## RX_SUMM_RADIATION_F=Beam + Imp or Isotopes 9 6 24.0 16.1
## RX_SUMM_RADIATION_F=Radiation, NOS 114 79 25.7 15.6
## RX_SUMM_RADIATION_F=Unknown 2196 598 NA 154.8
## 0.95UCL
## RX_SUMM_RADIATION_F=None NA
## RX_SUMM_RADIATION_F=Beam Radiation 16.2
## RX_SUMM_RADIATION_F=Radioactive Implants NA
## RX_SUMM_RADIATION_F=Radioisotopes NA
## RX_SUMM_RADIATION_F=Beam + Imp or Isotopes NA
## RX_SUMM_RADIATION_F=Radiation, NOS 35.7
## RX_SUMM_RADIATION_F=Unknown NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RX_SUMM_RADIATION_F, data = data)
##
## RX_SUMM_RADIATION_F=None
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 296059 16779 0.949 0.000383 0.948 0.950
## 24 255224 15967 0.896 0.000547 0.895 0.897
## 36 211644 12838 0.848 0.000662 0.846 0.849
## 48 174574 9535 0.807 0.000752 0.805 0.808
## 60 141423 7141 0.771 0.000829 0.769 0.773
## 120 33869 16672 0.628 0.001276 0.625 0.630
##
## RX_SUMM_RADIATION_F=Beam Radiation
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6075 5005 0.557 0.00469 0.548 0.566
## 24 4029 1546 0.409 0.00472 0.400 0.419
## 36 2806 733 0.330 0.00463 0.321 0.339
## 48 2054 359 0.284 0.00458 0.275 0.293
## 60 1507 208 0.253 0.00456 0.244 0.262
## 120 253 312 0.167 0.00542 0.157 0.178
##
## RX_SUMM_RADIATION_F=Radioactive Implants
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 36 6 0.861 0.0525 0.764 0.971
## 24 24 8 0.654 0.0755 0.522 0.820
## 36 17 2 0.589 0.0809 0.450 0.770
## 48 13 0 0.589 0.0809 0.450 0.770
## 60 11 1 0.543 0.0864 0.398 0.742
## 120 2 3 0.264 0.1302 0.100 0.694
##
## RX_SUMM_RADIATION_F=Radioisotopes
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7 1 0.889 0.105 0.706 1
## 24 6 1 0.762 0.148 0.521 1
## 36 6 0 0.762 0.148 0.521 1
## 48 4 2 0.508 0.177 0.257 1
## 60 4 0 0.508 0.177 0.257 1
##
## RX_SUMM_RADIATION_F=Beam + Imp or Isotopes
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 7 2 0.778 0.139 0.549 1.000
## 24 5 2 0.556 0.166 0.310 0.997
## 36 3 2 0.333 0.157 0.132 0.840
## 48 3 0 0.333 0.157 0.132 0.840
## 60 2 0 0.333 0.157 0.132 0.840
##
## RX_SUMM_RADIATION_F=Radiation, NOS
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 69 39 0.647 0.0456 0.564 0.743
## 24 50 14 0.513 0.0482 0.427 0.617
## 36 32 12 0.384 0.0485 0.300 0.491
## 48 25 4 0.332 0.0483 0.250 0.442
## 60 20 4 0.278 0.0474 0.199 0.389
## 120 6 3 0.208 0.0521 0.127 0.340
##
## RX_SUMM_RADIATION_F=Unknown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1904 115 0.945 0.00501 0.935 0.955
## 24 1721 85 0.902 0.00662 0.889 0.915
## 36 1571 64 0.867 0.00764 0.852 0.882
## 48 1461 49 0.839 0.00835 0.823 0.856
## 60 1335 56 0.807 0.00911 0.789 0.825
## 120 442 198 0.639 0.01323 0.613 0.665
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: RX_SUMM_RADIATION_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RX_SUMM_RADIATION_F, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef)
## RX_SUMM_RADIATION_FBeam Radiation 1.83534 6.26725 0.01167
## RX_SUMM_RADIATION_FRadioactive Implants 0.98420 2.67568 0.22364
## RX_SUMM_RADIATION_FRadioisotopes 0.88426 2.42118 0.44723
## RX_SUMM_RADIATION_FBeam + Imp or Isotopes 1.38614 3.99938 0.40826
## RX_SUMM_RADIATION_FRadiation, NOS 1.60332 4.96951 0.11257
## RX_SUMM_RADIATION_FUnknown -0.08043 0.92272 0.04105
## z Pr(>|z|)
## RX_SUMM_RADIATION_FBeam Radiation 157.210 < 2e-16 ***
## RX_SUMM_RADIATION_FRadioactive Implants 4.401 1.08e-05 ***
## RX_SUMM_RADIATION_FRadioisotopes 1.977 0.048020 *
## RX_SUMM_RADIATION_FBeam + Imp or Isotopes 3.395 0.000686 ***
## RX_SUMM_RADIATION_FRadiation, NOS 14.243 < 2e-16 ***
## RX_SUMM_RADIATION_FUnknown -1.959 0.050089 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95
## RX_SUMM_RADIATION_FBeam Radiation 6.2673 0.1596 6.1255
## RX_SUMM_RADIATION_FRadioactive Implants 2.6757 0.3737 1.7261
## RX_SUMM_RADIATION_FRadioisotopes 2.4212 0.4130 1.0077
## RX_SUMM_RADIATION_FBeam + Imp or Isotopes 3.9994 0.2500 1.7967
## RX_SUMM_RADIATION_FRadiation, NOS 4.9695 0.2012 3.9856
## RX_SUMM_RADIATION_FUnknown 0.9227 1.0838 0.8514
## upper .95
## RX_SUMM_RADIATION_FBeam Radiation 6.412
## RX_SUMM_RADIATION_FRadioactive Implants 4.148
## RX_SUMM_RADIATION_FRadioisotopes 5.817
## RX_SUMM_RADIATION_FBeam + Imp or Isotopes 8.902
## RX_SUMM_RADIATION_FRadiation, NOS 6.196
## RX_SUMM_RADIATION_FUnknown 1.000
##
## Concordance= 0.552 (se = 0 )
## Rsquare= 0.043 (max possible= 0.998 )
## Likelihood ratio test= 15804 on 6 df, p=0
## Wald test = 24931 on 6 df, p=0
## Score (logrank) test = 32711 on 6 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: RX_SUMM_RADIATION_F
Lymphovascular Invasion
uni_var(test_var = "LYMPH_VASCULAR_INVASION_F", data_imp = data)
## _________________________________________________
##
## ## LYMPH_VASCULAR_INVASION_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ LYMPH_VASCULAR_INVASION_F, data = data)
##
## 159900 observations deleted due to missingness
## n events median 0.95LCL
## LYMPH_VASCULAR_INVASION_F=Neg_LymphVasc_Inv 145065 21475 95.93 95.05
## LYMPH_VASCULAR_INVASION_F=Pos_LumphVasc_Inv 7694 3337 48.66 46.06
## LYMPH_VASCULAR_INVASION_F=N_A 50 30 8.87 6.87
## LYMPH_VASCULAR_INVASION_F=Unknown 50201 13034 94.62 94.03
## 0.95UCL
## LYMPH_VASCULAR_INVASION_F=Neg_LymphVasc_Inv NA
## LYMPH_VASCULAR_INVASION_F=Pos_LumphVasc_Inv 51.9
## LYMPH_VASCULAR_INVASION_F=N_A NA
## LYMPH_VASCULAR_INVASION_F=Unknown NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ LYMPH_VASCULAR_INVASION_F, data = data)
##
## 159900 observations deleted due to missingness
## LYMPH_VASCULAR_INVASION_F=Neg_LymphVasc_Inv
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 120432 4744 0.964 0.000508 0.963 0.965
## 24 97371 5627 0.916 0.000793 0.915 0.918
## 36 70251 4462 0.868 0.001026 0.866 0.870
## 48 47908 3006 0.825 0.001246 0.822 0.827
## 60 29223 1942 0.784 0.001498 0.781 0.787
##
## LYMPH_VASCULAR_INVASION_F=Pos_LumphVasc_Inv
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5771 1247 0.830 0.00440 0.821 0.838
## 24 4077 1019 0.674 0.00567 0.663 0.686
## 36 2690 553 0.573 0.00626 0.561 0.585
## 48 1720 284 0.503 0.00675 0.490 0.516
## 60 969 134 0.455 0.00730 0.441 0.469
##
## LYMPH_VASCULAR_INVASION_F=N_A
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 18 25 0.471 0.0734 0.3470 0.639
## 24 7 3 0.369 0.0783 0.2434 0.559
## 36 1 2 0.197 0.1007 0.0722 0.536
##
## LYMPH_VASCULAR_INVASION_F=Unknown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 37970 6232 0.869 0.00155 0.866 0.872
## 24 30826 2671 0.804 0.00188 0.800 0.808
## 36 23552 1715 0.755 0.00211 0.750 0.759
## 48 17056 1098 0.715 0.00232 0.710 0.719
## 60 10962 668 0.681 0.00255 0.676 0.686
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: LYMPH_VASCULAR_INVASION_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ LYMPH_VASCULAR_INVASION_F, data = data)
##
## n= 203010, number of events= 37876
## (159900 observations deleted due to missingness)
##
## coef exp(coef) se(coef)
## LYMPH_VASCULAR_INVASION_FPos_LumphVasc_Inv 1.26944 3.55885 0.01862
## LYMPH_VASCULAR_INVASION_FN_A 2.54386 12.72866 0.18275
## LYMPH_VASCULAR_INVASION_FUnknown 0.60603 1.83314 0.01111
## z Pr(>|z|)
## LYMPH_VASCULAR_INVASION_FPos_LumphVasc_Inv 68.17 <2e-16 ***
## LYMPH_VASCULAR_INVASION_FN_A 13.92 <2e-16 ***
## LYMPH_VASCULAR_INVASION_FUnknown 54.56 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95
## LYMPH_VASCULAR_INVASION_FPos_LumphVasc_Inv 3.559 0.28099 3.431
## LYMPH_VASCULAR_INVASION_FN_A 12.729 0.07856 8.897
## LYMPH_VASCULAR_INVASION_FUnknown 1.833 0.54551 1.794
## upper .95
## LYMPH_VASCULAR_INVASION_FPos_LumphVasc_Inv 3.691
## LYMPH_VASCULAR_INVASION_FN_A 18.211
## LYMPH_VASCULAR_INVASION_FUnknown 1.873
##
## Concordance= 0.609 (se = 0.001 )
## Rsquare= 0.027 (max possible= 0.987 )
## Likelihood ratio test= 5553 on 3 df, p=0
## Wald test = 6417 on 3 df, p=0
## Score (logrank) test = 7039 on 3 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: LYMPH_VASCULAR_INVASION_F
Endoscopic/Robotic
uni_var(test_var = "RX_HOSP_SURG_APPR_2010_F", data_imp = data)
## _________________________________________________
##
## ## RX_HOSP_SURG_APPR_2010_F
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RX_HOSP_SURG_APPR_2010_F, data = data)
##
## 159900 observations deleted due to missingness
## n events median 0.95LCL
## RX_HOSP_SURG_APPR_2010_F=No_Surg 18689 8965 36.0 33.97
## RX_HOSP_SURG_APPR_2010_F=Robot_Assist 148 26 NA NA
## RX_HOSP_SURG_APPR_2010_F=Robot_to_Open 37 5 NA 56.71
## RX_HOSP_SURG_APPR_2010_F=Endo_Lap 441 109 NA 85.29
## RX_HOSP_SURG_APPR_2010_F=Endo_Lap_to_Open 170 31 NA 81.51
## RX_HOSP_SURG_APPR_2010_F=Open_Unknown 183492 28727 95.5 95.05
## RX_HOSP_SURG_APPR_2010_F=Unknown 33 13 14.8 6.24
## 0.95UCL
## RX_HOSP_SURG_APPR_2010_F=No_Surg 37.9
## RX_HOSP_SURG_APPR_2010_F=Robot_Assist NA
## RX_HOSP_SURG_APPR_2010_F=Robot_to_Open NA
## RX_HOSP_SURG_APPR_2010_F=Endo_Lap NA
## RX_HOSP_SURG_APPR_2010_F=Endo_Lap_to_Open NA
## RX_HOSP_SURG_APPR_2010_F=Open_Unknown NA
## RX_HOSP_SURG_APPR_2010_F=Unknown NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RX_HOSP_SURG_APPR_2010_F, data = data)
##
## 159900 observations deleted due to missingness
## RX_HOSP_SURG_APPR_2010_F=No_Surg
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 10832 5927 0.665 0.00356 0.659 0.672
## 24 7778 1575 0.562 0.00385 0.555 0.570
## 36 5216 764 0.500 0.00404 0.492 0.508
## 48 3429 385 0.457 0.00425 0.449 0.465
## 60 2057 170 0.429 0.00452 0.420 0.438
##
## RX_HOSP_SURG_APPR_2010_F=Robot_Assist
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 121 8 0.941 0.0204 0.902 0.981
## 24 99 6 0.890 0.0280 0.836 0.946
## 36 74 6 0.828 0.0357 0.761 0.901
## 48 48 3 0.791 0.0400 0.716 0.873
## 60 24 1 0.766 0.0458 0.681 0.861
##
## RX_HOSP_SURG_APPR_2010_F=Robot_to_Open
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 28 3 0.908 0.0508 0.814 1
## 24 21 0 0.908 0.0508 0.814 1
## 36 17 0 0.908 0.0508 0.814 1
## 48 12 0 0.908 0.0508 0.814 1
## 60 2 2 0.692 0.1398 0.465 1
##
## RX_HOSP_SURG_APPR_2010_F=Endo_Lap
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 342 38 0.906 0.0145 0.878 0.935
## 24 269 24 0.837 0.0190 0.801 0.876
## 36 189 24 0.753 0.0237 0.708 0.801
## 48 122 14 0.687 0.0275 0.635 0.743
## 60 66 8 0.636 0.0308 0.579 0.700
##
## RX_HOSP_SURG_APPR_2010_F=Endo_Lap_to_Open
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 134 7 0.954 0.0169 0.922 0.988
## 24 119 4 0.924 0.0221 0.882 0.968
## 36 101 6 0.874 0.0289 0.819 0.932
## 48 73 3 0.845 0.0324 0.784 0.911
## 60 54 1 0.833 0.0341 0.769 0.903
##
## RX_HOSP_SURG_APPR_2010_F=Open_Unknown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 152722 6256 0.963 0.000460 0.962 0.964
## 24 123988 7707 0.911 0.000723 0.910 0.912
## 36 90891 5932 0.862 0.000925 0.860 0.864
## 48 62997 3983 0.818 0.001110 0.816 0.820
## 60 38949 2562 0.777 0.001317 0.775 0.780
##
## RX_HOSP_SURG_APPR_2010_F=Unknown
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 12 9 0.601 0.105 0.427 0.846
## 24 7 4 0.401 0.108 0.237 0.679
## 36 6 0 0.401 0.108 0.237 0.679
## 48 3 0 0.401 0.108 0.237 0.679
## 60 2 0 0.401 0.108 0.237 0.679
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: RX_HOSP_SURG_APPR_2010_F
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RX_HOSP_SURG_APPR_2010_F, data = data)
##
## n= 203010, number of events= 37876
## (159900 observations deleted due to missingness)
##
## coef exp(coef) se(coef)
## RX_HOSP_SURG_APPR_2010_FRobot_Assist -1.40546 0.24526 0.19640
## RX_HOSP_SURG_APPR_2010_FRobot_to_Open -1.52765 0.21705 0.44734
## RX_HOSP_SURG_APPR_2010_FEndo_Lap -0.96163 0.38227 0.09637
## RX_HOSP_SURG_APPR_2010_FEndo_Lap_to_Open -1.49545 0.22415 0.17993
## RX_HOSP_SURG_APPR_2010_FOpen_Unknown -1.53853 0.21470 0.01213
## RX_HOSP_SURG_APPR_2010_FUnknown 0.33426 1.39691 0.27755
## z Pr(>|z|)
## RX_HOSP_SURG_APPR_2010_FRobot_Assist -7.156 8.31e-13 ***
## RX_HOSP_SURG_APPR_2010_FRobot_to_Open -3.415 0.000638 ***
## RX_HOSP_SURG_APPR_2010_FEndo_Lap -9.979 < 2e-16 ***
## RX_HOSP_SURG_APPR_2010_FEndo_Lap_to_Open -8.312 < 2e-16 ***
## RX_HOSP_SURG_APPR_2010_FOpen_Unknown -126.816 < 2e-16 ***
## RX_HOSP_SURG_APPR_2010_FUnknown 1.204 0.228472
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95
## RX_HOSP_SURG_APPR_2010_FRobot_Assist 0.2453 4.0774 0.16689
## RX_HOSP_SURG_APPR_2010_FRobot_to_Open 0.2170 4.6073 0.09032
## RX_HOSP_SURG_APPR_2010_FEndo_Lap 0.3823 2.6160 0.31648
## RX_HOSP_SURG_APPR_2010_FEndo_Lap_to_Open 0.2241 4.4614 0.15754
## RX_HOSP_SURG_APPR_2010_FOpen_Unknown 0.2147 4.6577 0.20965
## RX_HOSP_SURG_APPR_2010_FUnknown 1.3969 0.7159 0.81080
## upper .95
## RX_HOSP_SURG_APPR_2010_FRobot_Assist 0.3604
## RX_HOSP_SURG_APPR_2010_FRobot_to_Open 0.5216
## RX_HOSP_SURG_APPR_2010_FEndo_Lap 0.4617
## RX_HOSP_SURG_APPR_2010_FEndo_Lap_to_Open 0.3189
## RX_HOSP_SURG_APPR_2010_FOpen_Unknown 0.2199
## RX_HOSP_SURG_APPR_2010_FUnknown 2.4067
##
## Concordance= 0.617 (se = 0.001 )
## Rsquare= 0.057 (max possible= 0.987 )
## Likelihood ratio test= 11999 on 6 df, p=0
## Wald test = 16121 on 6 df, p=0
## Score (logrank) test = 19537 on 6 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: RX_HOSP_SURG_APPR_2010_F
Surgery Radiation Sequence
uni_var(test_var = "SURG_RAD_SEQ", data_imp = data)
## _________________________________________________
##
## ## SURG_RAD_SEQ
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURG_RAD_SEQ, data = data)
##
## n events median 0.95LCL
## SURG_RAD_SEQ=Surg Alone 337579 73170 NA 164.60
## SURG_RAD_SEQ=Surg then Rad 6249 3820 32.16 30.78
## SURG_RAD_SEQ=Rad Alone 5240 4377 6.14 5.88
## SURG_RAD_SEQ=No Treatment 10837 7403 11.43 10.97
## SURG_RAD_SEQ=Other 2891 1115 132.83 120.51
## SURG_RAD_SEQ=Rad before and after Surg 17 14 9.07 4.01
## SURG_RAD_SEQ=Rad then Surg 97 73 15.21 10.87
## 0.95UCL
## SURG_RAD_SEQ=Surg Alone NA
## SURG_RAD_SEQ=Surg then Rad 33.77
## SURG_RAD_SEQ=Rad Alone 6.51
## SURG_RAD_SEQ=No Treatment 12.00
## SURG_RAD_SEQ=Other 150.70
## SURG_RAD_SEQ=Rad before and after Surg 24.11
## SURG_RAD_SEQ=Rad then Surg 23.49
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURG_RAD_SEQ, data = data)
##
## SURG_RAD_SEQ=Surg Alone
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 291152 11156 0.965 0.000328 0.964 0.965
## 24 251965 14780 0.914 0.000514 0.913 0.915
## 36 209336 12350 0.866 0.000642 0.865 0.867
## 48 172875 9282 0.825 0.000741 0.823 0.826
## 60 140127 7012 0.788 0.000826 0.787 0.790
## 120 33580 16468 0.642 0.001299 0.640 0.645
##
## SURG_RAD_SEQ=Surg then Rad
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4522 1515 0.753 0.00550 0.743 0.764
## 24 3177 999 0.581 0.00642 0.568 0.593
## 36 2276 561 0.472 0.00666 0.459 0.485
## 48 1677 287 0.408 0.00675 0.395 0.421
## 60 1238 174 0.362 0.00684 0.348 0.375
## 120 209 262 0.237 0.00844 0.221 0.254
##
## SURG_RAD_SEQ=Rad Alone
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 1594 3476 0.3258 0.00657 0.3132 0.339
## 24 886 551 0.2074 0.00582 0.1963 0.219
## 36 552 180 0.1609 0.00546 0.1505 0.172
## 48 392 76 0.1369 0.00530 0.1269 0.148
## 60 280 38 0.1225 0.00524 0.1126 0.133
## 120 45 48 0.0874 0.00613 0.0762 0.100
##
## SURG_RAD_SEQ=No Treatment
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 4680 5246 0.490 0.00496 0.480 0.500
## 24 3105 1132 0.366 0.00490 0.356 0.376
## 36 2195 459 0.308 0.00482 0.298 0.317
## 48 1608 241 0.271 0.00480 0.261 0.280
## 60 1225 115 0.249 0.00482 0.240 0.259
## 120 272 191 0.191 0.00542 0.181 0.202
##
## SURG_RAD_SEQ=Other
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 2148 502 0.818 0.00736 0.804 0.832
## 24 1888 141 0.763 0.00820 0.747 0.779
## 36 1694 93 0.724 0.00871 0.707 0.741
## 48 1559 63 0.697 0.00904 0.679 0.715
## 60 1413 70 0.665 0.00940 0.646 0.683
## 120 459 214 0.524 0.01160 0.502 0.547
##
## SURG_RAD_SEQ=Rad before and after Surg
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6 11 0.353 0.1159 0.1854 0.672
## 24 4 2 0.235 0.1029 0.0999 0.554
## 36 3 1 0.176 0.0925 0.0632 0.493
## 48 3 0 0.176 0.0925 0.0632 0.493
## 60 3 0 0.176 0.0925 0.0632 0.493
## 120 3 0 0.176 0.0925 0.0632 0.493
##
## SURG_RAD_SEQ=Rad then Surg
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 55 41 0.571 0.0507 0.4798 0.680
## 24 34 18 0.378 0.0500 0.2914 0.490
## 36 23 7 0.295 0.0480 0.2148 0.406
## 48 20 0 0.295 0.0480 0.2148 0.406
## 60 16 1 0.279 0.0480 0.1991 0.391
## 120 4 6 0.109 0.0508 0.0439 0.272
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: SURG_RAD_SEQ
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURG_RAD_SEQ, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z
## SURG_RAD_SEQSurg then Rad 1.46805 4.34076 0.01663 88.286
## SURG_RAD_SEQRad Alone 2.66145 14.31699 0.01575 168.937
## SURG_RAD_SEQNo Treatment 2.06172 7.85949 0.01226 168.104
## SURG_RAD_SEQOther 0.54046 1.71679 0.03018 17.905
## SURG_RAD_SEQRad before and after Surg 2.01488 7.49982 0.26729 7.538
## SURG_RAD_SEQRad then Surg 1.93211 6.90408 0.11711 16.499
## Pr(>|z|)
## SURG_RAD_SEQSurg then Rad < 2e-16 ***
## SURG_RAD_SEQRad Alone < 2e-16 ***
## SURG_RAD_SEQNo Treatment < 2e-16 ***
## SURG_RAD_SEQOther < 2e-16 ***
## SURG_RAD_SEQRad before and after Surg 4.77e-14 ***
## SURG_RAD_SEQRad then Surg < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95
## SURG_RAD_SEQSurg then Rad 4.341 0.23037 4.202
## SURG_RAD_SEQRad Alone 14.317 0.06985 13.882
## SURG_RAD_SEQNo Treatment 7.859 0.12723 7.673
## SURG_RAD_SEQOther 1.717 0.58248 1.618
## SURG_RAD_SEQRad before and after Surg 7.500 0.13334 4.441
## SURG_RAD_SEQRad then Surg 6.904 0.14484 5.488
## upper .95
## SURG_RAD_SEQSurg then Rad 4.485
## SURG_RAD_SEQRad Alone 14.766
## SURG_RAD_SEQNo Treatment 8.051
## SURG_RAD_SEQOther 1.821
## SURG_RAD_SEQRad before and after Surg 12.664
## SURG_RAD_SEQRad then Surg 8.685
##
## Concordance= 0.605 (se = 0 )
## Rsquare= 0.094 (max possible= 0.998 )
## Likelihood ratio test= 35691 on 6 df, p=0
## Wald test = 57107 on 6 df, p=0
## Score (logrank) test = 86266 on 6 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: SURG_RAD_SEQ
Surgery Yes/No
uni_var(test_var = "SURGERY_YN", data_imp = data)
## _________________________________________________
##
## ## SURGERY_YN
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURGERY_YN, data = data)
##
## n events median 0.95LCL 0.95UCL
## SURGERY_YN=No 16214 11864 8.77 8.48 9.1
## SURGERY_YN=Ukn 684 462 14.19 11.83 16.4
## SURGERY_YN=Yes 346012 77646 165.39 164.57 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURGERY_YN, data = data)
##
## SURGERY_YN=No
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6305 8805 0.434 0.00400 0.426 0.442
## 24 4021 1679 0.313 0.00383 0.305 0.320
## 36 2771 641 0.259 0.00372 0.251 0.266
## 48 2025 316 0.226 0.00367 0.219 0.234
## 60 1528 153 0.208 0.00367 0.201 0.215
## 120 323 243 0.157 0.00413 0.149 0.166
##
## SURGERY_YN=Ukn
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 310 291 0.533 0.0201 0.495 0.574
## 24 205 79 0.392 0.0201 0.355 0.433
## 36 148 37 0.316 0.0197 0.280 0.357
## 48 120 15 0.282 0.0195 0.247 0.323
## 60 93 18 0.238 0.0190 0.204 0.279
## 120 22 21 0.172 0.0186 0.139 0.212
##
## SURGERY_YN=Yes
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 297542 12851 0.960 0.000342 0.960 0.961
## 24 256833 15865 0.907 0.000524 0.906 0.908
## 36 213160 12973 0.858 0.000648 0.857 0.859
## 48 175989 9618 0.817 0.000743 0.815 0.818
## 60 142681 7239 0.780 0.000824 0.779 0.782
## 120 34227 16925 0.635 0.001283 0.632 0.637
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: SURGERY_YN
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURGERY_YN, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## SURGERY_YNUkn -0.27473 0.75977 0.04742 -5.793 6.91e-09 ***
## SURGERY_YNYes -2.19889 0.11093 0.00998 -220.333 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## SURGERY_YNUkn 0.7598 1.316 0.6923 0.8338
## SURGERY_YNYes 0.1109 9.015 0.1088 0.1131
##
## Concordance= 0.585 (se = 0 )
## Rsquare= 0.08 (max possible= 0.998 )
## Likelihood ratio test= 30337 on 2 df, p=0
## Wald test = 49726 on 2 df, p=0
## Score (logrank) test = 72791 on 2 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: SURGERY_YN
Radiation Yes/No
uni_var(test_var = "RADIATION_YN", data_imp = data)
## _________________________________________________
##
## ## RADIATION_YN
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RADIATION_YN, data = data)
##
## 2370 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## RADIATION_YN=No 348906 80900 164.7 164.5 NA
## RADIATION_YN=Yes 11634 8300 15.7 15.1 16.4
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RADIATION_YN, data = data)
##
## 2370 observations deleted due to missingness
## RADIATION_YN=No
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 296056 16607 0.950 0.000381 0.949 0.950
## 24 255222 15967 0.896 0.000546 0.895 0.897
## 36 211643 12837 0.848 0.000662 0.847 0.849
## 48 174573 9535 0.807 0.000752 0.806 0.809
## 60 141422 7141 0.771 0.000829 0.770 0.773
## 120 33869 16671 0.628 0.001277 0.626 0.631
##
## RADIATION_YN=Yes
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 6194 5053 0.559 0.00465 0.550 0.569
## 24 4114 1571 0.412 0.00469 0.402 0.421
## 36 2864 749 0.331 0.00460 0.323 0.341
## 48 2099 365 0.286 0.00455 0.277 0.295
## 60 1544 213 0.254 0.00454 0.246 0.263
## 120 261 319 0.168 0.00540 0.158 0.179
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: RADIATION_YN
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ RADIATION_YN, data = data)
##
## n= 360540, number of events= 89200
## (2370 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## RADIATION_YNYes 1.83188 6.24562 0.01161 157.9 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## RADIATION_YNYes 6.246 0.1601 6.105 6.389
##
## Concordance= 0.552 (se = 0 )
## Rsquare= 0.043 (max possible= 0.998 )
## Likelihood ratio test= 15806 on 1 df, p=0
## Wald test = 24917 on 1 df, p=0
## Score (logrank) test = 32677 on 1 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: RADIATION_YN
Chemo Yes/No
uni_var(test_var = "CHEMO_YN", data_imp = data)
## _________________________________________________
##
## ## CHEMO_YN
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ CHEMO_YN, data = data)
##
## n events median 0.95LCL 0.95UCL
## CHEMO_YN=No 342669 80729 164.6 164.4 NA
## CHEMO_YN=Yes 9216 6400 16.6 15.8 17.2
## CHEMO_YN=Ukn 11025 2843 NA 160.7 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ CHEMO_YN, data = data)
##
## CHEMO_YN=No
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 289704 17488 0.946 0.000396 0.945 0.947
## 24 249482 15703 0.893 0.000559 0.892 0.894
## 36 206545 12671 0.844 0.000674 0.843 0.846
## 48 170118 9390 0.803 0.000764 0.802 0.805
## 60 137619 7033 0.767 0.000842 0.765 0.769
## 120 32671 16359 0.623 0.001295 0.621 0.626
##
## CHEMO_YN=Yes
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 5063 3783 0.581 0.00521 0.571 0.591
## 24 3350 1399 0.415 0.00529 0.405 0.426
## 36 2470 559 0.342 0.00518 0.332 0.353
## 48 1923 272 0.303 0.00511 0.293 0.313
## 60 1520 133 0.280 0.00509 0.270 0.290
## 120 371 228 0.220 0.00551 0.210 0.231
##
## CHEMO_YN=Ukn
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 9390 676 0.936 0.00239 0.931 0.940
## 24 8227 521 0.882 0.00321 0.876 0.888
## 36 7064 421 0.835 0.00378 0.827 0.842
## 48 6093 287 0.799 0.00417 0.791 0.807
## 60 5163 244 0.765 0.00452 0.756 0.774
## 120 1530 602 0.635 0.00635 0.622 0.647
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: CHEMO_YN
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ CHEMO_YN, data = data)
##
## n= 362910, number of events= 89972
##
## coef exp(coef) se(coef) z Pr(>|z|)
## CHEMO_YNYes 1.670322 5.313878 0.013030 128.186 <2e-16 ***
## CHEMO_YNUkn -0.003705 0.996302 0.019086 -0.194 0.846
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## CHEMO_YNYes 5.3139 0.1882 5.1799 5.451
## CHEMO_YNUkn 0.9963 1.0037 0.9597 1.034
##
## Concordance= 0.538 (se = 0 )
## Rsquare= 0.029 (max possible= 0.998 )
## Likelihood ratio test= 10647 on 2 df, p=0
## Wald test = 16474 on 2 df, p=0
## Score (logrank) test = 20670 on 2 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: CHEMO_YN
Treatment Yes/No
uni_var(test_var = "Tx_YN", data_imp = data)
## _________________________________________________
##
## ## Tx_YN
## _________________________________________________
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ Tx_YN, data = data)
##
## 11025 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## Tx_YN=FALSE 8215 5411 12 11.2 12.8
## Tx_YN=TRUE 343670 81718 165 164.4 NA
##
## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ Tx_YN, data = data)
##
## 11025 observations deleted due to missingness
## Tx_YN=FALSE
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 3583 3896 0.500 0.00571 0.489 0.511
## 24 2501 723 0.394 0.00570 0.383 0.405
## 36 1796 340 0.336 0.00567 0.325 0.347
## 48 1323 182 0.299 0.00568 0.288 0.310
## 60 1017 90 0.276 0.00573 0.265 0.288
## 120 212 166 0.208 0.00660 0.195 0.221
##
## Tx_YN=TRUE
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 12 291184 17375 0.946 0.000396 0.946 0.947
## 24 250331 16379 0.891 0.000562 0.890 0.892
## 36 207219 12890 0.842 0.000677 0.841 0.843
## 48 170718 9480 0.801 0.000766 0.799 0.802
## 60 138122 7076 0.765 0.000843 0.763 0.766
## 120 32830 16421 0.621 0.001290 0.619 0.624
##
##
##
##
##
## ## Univariable Cox Proportional Hazard Model for: Tx_YN
##
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ Tx_YN, data = data)
##
## n= 351885, number of events= 87129
## (11025 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## Tx_YNTRUE -1.86336 0.15515 0.01408 -132.3 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## Tx_YNTRUE 0.1552 6.445 0.1509 0.1595
##
## Concordance= 0.537 (se = 0 )
## Rsquare= 0.03 (max possible= 0.998 )
## Likelihood ratio test= 10747 on 1 df, p=0
## Wald test = 17504 on 1 df, p=0
## Score (logrank) test = 23183 on 1 df, p=0
##
##
##
##
##
##
## ## Unadjusted Kaplan Meier Overall Survival Curve for: Tx_YN
Tumor specific Variables
Node Size
Cox Proportional Hazard Ratio
Model #1
Full analysis
model_one <- coxph(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS == 0)
~ SURG_RAD_SEQ + INSURANCE_F + AGE + SEX_F + RACE_F + INCOME_F + U_R_F +
FACILITY_TYPE_F + FACILITY_LOCATION_F + EDUCATION_F,
data = data)
model_one %>% summary()
## Call:
## coxph(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS ==
## 0) ~ SURG_RAD_SEQ + INSURANCE_F + AGE + SEX_F + RACE_F +
## INCOME_F + U_R_F + FACILITY_TYPE_F + FACILITY_LOCATION_F +
## EDUCATION_F, data = data)
##
## n= 310618, number of events= 84098
## (52292 observations deleted due to missingness)
##
## coef exp(coef) se(coef)
## SURG_RAD_SEQSurg then Rad 1.175093 3.238443 0.017436
## SURG_RAD_SEQRad Alone 2.488459 12.042700 0.016545
## SURG_RAD_SEQNo Treatment 1.918921 6.813599 0.012812
## SURG_RAD_SEQOther 0.527635 1.694918 0.031302
## SURG_RAD_SEQRad before and after Surg 2.664354 14.358675 0.288773
## SURG_RAD_SEQRad then Surg 1.634362 5.126184 0.126140
## INSURANCE_FNone 0.816196 2.261881 0.023242
## INSURANCE_FMedicaid 0.950788 2.587747 0.021840
## INSURANCE_FMedicare 0.172193 1.187907 0.009972
## INSURANCE_FOther Government 0.226541 1.254254 0.037211
## INSURANCE_FUnknown NA NA 0.000000
## AGE 0.055292 1.056849 0.000389
## SEX_FFemale -0.317842 0.727718 0.007424
## RACE_FBlack 0.402027 1.494852 0.035050
## RACE_FOther/Unk -0.089698 0.914207 0.030340
## RACE_FAsian 0.228528 1.256749 0.061677
## INCOME_F$38,000 - $47,999 -0.047120 0.953973 0.012448
## INCOME_F$48,000 - $62,999 -0.080485 0.922669 0.013199
## INCOME_F$63,000 + -0.148064 0.862376 0.014837
## U_R_FUrban -0.035235 0.965379 0.010583
## U_R_FRural -0.011491 0.988575 0.024840
## FACILITY_TYPE_FComprehensive Comm Ca Program -0.046446 0.954616 0.013827
## FACILITY_TYPE_FAcademic/Research Program -0.137317 0.871694 0.013803
## FACILITY_TYPE_FIntegrated Network Ca Program -0.019513 0.980677 0.016205
## FACILITY_LOCATION_FMiddle Atlantic -0.004003 0.996005 0.016806
## FACILITY_LOCATION_FSouth Atlantic -0.027797 0.972586 0.016273
## FACILITY_LOCATION_FEast North Central 0.073783 1.076573 0.016696
## FACILITY_LOCATION_FEast South Central 0.062075 1.064043 0.019632
## FACILITY_LOCATION_FWest North Central 0.033008 1.033559 0.019111
## FACILITY_LOCATION_FWest South Central 0.015189 1.015304 0.020821
## FACILITY_LOCATION_FMountain 0.021827 1.022067 0.021098
## FACILITY_LOCATION_FPacific -0.053757 0.947662 0.017688
## EDUCATION_F13 - 20.9% -0.067335 0.934882 0.012642
## EDUCATION_F7 - 12.9% -0.117863 0.888818 0.013357
## EDUCATION_FLess than 7% -0.255588 0.774461 0.015259
## z Pr(>|z|)
## SURG_RAD_SEQSurg then Rad 67.395 < 2e-16 ***
## SURG_RAD_SEQRad Alone 150.404 < 2e-16 ***
## SURG_RAD_SEQNo Treatment 149.775 < 2e-16 ***
## SURG_RAD_SEQOther 16.856 < 2e-16 ***
## SURG_RAD_SEQRad before and after Surg 9.226 < 2e-16 ***
## SURG_RAD_SEQRad then Surg 12.957 < 2e-16 ***
## INSURANCE_FNone 35.117 < 2e-16 ***
## INSURANCE_FMedicaid 43.535 < 2e-16 ***
## INSURANCE_FMedicare 17.268 < 2e-16 ***
## INSURANCE_FOther Government 6.088 1.14e-09 ***
## INSURANCE_FUnknown NA NA
## AGE 142.146 < 2e-16 ***
## SEX_FFemale -42.811 < 2e-16 ***
## RACE_FBlack 11.470 < 2e-16 ***
## RACE_FOther/Unk -2.956 0.003112 **
## RACE_FAsian 3.705 0.000211 ***
## INCOME_F$38,000 - $47,999 -3.785 0.000153 ***
## INCOME_F$48,000 - $62,999 -6.098 1.08e-09 ***
## INCOME_F$63,000 + -9.979 < 2e-16 ***
## U_R_FUrban -3.329 0.000871 ***
## U_R_FRural -0.463 0.643647
## FACILITY_TYPE_FComprehensive Comm Ca Program -3.359 0.000782 ***
## FACILITY_TYPE_FAcademic/Research Program -9.949 < 2e-16 ***
## FACILITY_TYPE_FIntegrated Network Ca Program -1.204 0.228544
## FACILITY_LOCATION_FMiddle Atlantic -0.238 0.811730
## FACILITY_LOCATION_FSouth Atlantic -1.708 0.087608 .
## FACILITY_LOCATION_FEast North Central 4.419 9.90e-06 ***
## FACILITY_LOCATION_FEast South Central 3.162 0.001567 **
## FACILITY_LOCATION_FWest North Central 1.727 0.084140 .
## FACILITY_LOCATION_FWest South Central 0.729 0.465706
## FACILITY_LOCATION_FMountain 1.035 0.300893
## FACILITY_LOCATION_FPacific -3.039 0.002372 **
## EDUCATION_F13 - 20.9% -5.326 1.00e-07 ***
## EDUCATION_F7 - 12.9% -8.824 < 2e-16 ***
## EDUCATION_FLess than 7% -16.750 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef)
## SURG_RAD_SEQSurg then Rad 3.2384 0.30879
## SURG_RAD_SEQRad Alone 12.0427 0.08304
## SURG_RAD_SEQNo Treatment 6.8136 0.14677
## SURG_RAD_SEQOther 1.6949 0.59000
## SURG_RAD_SEQRad before and after Surg 14.3587 0.06964
## SURG_RAD_SEQRad then Surg 5.1262 0.19508
## INSURANCE_FNone 2.2619 0.44211
## INSURANCE_FMedicaid 2.5877 0.38644
## INSURANCE_FMedicare 1.1879 0.84182
## INSURANCE_FOther Government 1.2543 0.79729
## INSURANCE_FUnknown NA NA
## AGE 1.0568 0.94621
## SEX_FFemale 0.7277 1.37416
## RACE_FBlack 1.4949 0.66896
## RACE_FOther/Unk 0.9142 1.09384
## RACE_FAsian 1.2567 0.79570
## INCOME_F$38,000 - $47,999 0.9540 1.04825
## INCOME_F$48,000 - $62,999 0.9227 1.08381
## INCOME_F$63,000 + 0.8624 1.15959
## U_R_FUrban 0.9654 1.03586
## U_R_FRural 0.9886 1.01156
## FACILITY_TYPE_FComprehensive Comm Ca Program 0.9546 1.04754
## FACILITY_TYPE_FAcademic/Research Program 0.8717 1.14719
## FACILITY_TYPE_FIntegrated Network Ca Program 0.9807 1.01970
## FACILITY_LOCATION_FMiddle Atlantic 0.9960 1.00401
## FACILITY_LOCATION_FSouth Atlantic 0.9726 1.02819
## FACILITY_LOCATION_FEast North Central 1.0766 0.92887
## FACILITY_LOCATION_FEast South Central 1.0640 0.93981
## FACILITY_LOCATION_FWest North Central 1.0336 0.96753
## FACILITY_LOCATION_FWest South Central 1.0153 0.98493
## FACILITY_LOCATION_FMountain 1.0221 0.97841
## FACILITY_LOCATION_FPacific 0.9477 1.05523
## EDUCATION_F13 - 20.9% 0.9349 1.06965
## EDUCATION_F7 - 12.9% 0.8888 1.12509
## EDUCATION_FLess than 7% 0.7745 1.29122
## lower .95 upper .95
## SURG_RAD_SEQSurg then Rad 3.1296 3.3510
## SURG_RAD_SEQRad Alone 11.6584 12.4396
## SURG_RAD_SEQNo Treatment 6.6446 6.9869
## SURG_RAD_SEQOther 1.5941 1.8022
## SURG_RAD_SEQRad before and after Surg 8.1529 25.2882
## SURG_RAD_SEQRad then Surg 4.0033 6.5639
## INSURANCE_FNone 2.1612 2.3673
## INSURANCE_FMedicaid 2.4793 2.7009
## INSURANCE_FMedicare 1.1649 1.2114
## INSURANCE_FOther Government 1.1660 1.3491
## INSURANCE_FUnknown NA NA
## AGE 1.0560 1.0577
## SEX_FFemale 0.7172 0.7384
## RACE_FBlack 1.3956 1.6012
## RACE_FOther/Unk 0.8614 0.9702
## RACE_FAsian 1.1136 1.4182
## INCOME_F$38,000 - $47,999 0.9310 0.9775
## INCOME_F$48,000 - $62,999 0.8991 0.9468
## INCOME_F$63,000 + 0.8377 0.8878
## U_R_FUrban 0.9456 0.9856
## U_R_FRural 0.9416 1.0379
## FACILITY_TYPE_FComprehensive Comm Ca Program 0.9291 0.9808
## FACILITY_TYPE_FAcademic/Research Program 0.8484 0.8956
## FACILITY_TYPE_FIntegrated Network Ca Program 0.9500 1.0123
## FACILITY_LOCATION_FMiddle Atlantic 0.9637 1.0294
## FACILITY_LOCATION_FSouth Atlantic 0.9421 1.0041
## FACILITY_LOCATION_FEast North Central 1.0419 1.1124
## FACILITY_LOCATION_FEast South Central 1.0239 1.1058
## FACILITY_LOCATION_FWest North Central 0.9956 1.0730
## FACILITY_LOCATION_FWest South Central 0.9747 1.0576
## FACILITY_LOCATION_FMountain 0.9807 1.0652
## FACILITY_LOCATION_FPacific 0.9154 0.9811
## EDUCATION_F13 - 20.9% 0.9120 0.9583
## EDUCATION_F7 - 12.9% 0.8659 0.9124
## EDUCATION_FLess than 7% 0.7516 0.7980
##
## Concordance= 0.767 (se = 0.001 )
## Rsquare= 0.226 (max possible= 0.999 )
## Likelihood ratio test= 79560 on 34 df, p=0
## Wald test = 91341 on 34 df, p=0
## Score (logrank) test = 120014 on 34 df, p=0
Summary of Model
model_one %>%
tidy(., exponentiate = TRUE) %>%
select(term, estimate, conf.low, conf.high, p.value) %>%
rename(Variable = term,
Hazard_Ratio = estimate) %>%
tbl_df %>%
print(n = nrow(.))
## # A tibble: 35 x 5
## Variable Hazard_Ratio conf.low
## <chr> <dbl> <dbl>
## 1 SURG_RAD_SEQSurg then Rad 3.2384432 3.1296434
## 2 SURG_RAD_SEQRad Alone 12.0426996 11.6584439
## 3 SURG_RAD_SEQNo Treatment 6.8135992 6.6446328
## 4 SURG_RAD_SEQOther 1.6949182 1.5940590
## 5 SURG_RAD_SEQRad before and after Surg 14.3586752 8.1528685
## 6 SURG_RAD_SEQRad then Surg 5.1261839 4.0033497
## 7 INSURANCE_FNone 2.2618805 2.1611550
## 8 INSURANCE_FMedicaid 2.5877467 2.4793148
## 9 INSURANCE_FMedicare 1.1879067 1.1649148
## 10 INSURANCE_FOther Government 1.2542538 1.1660347
## 11 INSURANCE_FUnknown NA NA
## 12 AGE 1.0568495 1.0560440
## 13 SEX_FFemale 0.7277177 0.7172049
## 14 RACE_FBlack 1.4948519 1.3956069
## 15 RACE_FOther/Unk 0.9142072 0.8614287
## 16 RACE_FAsian 1.2567485 1.1136500
## 17 INCOME_F$38,000 - $47,999 0.9539725 0.9309795
## 18 INCOME_F$48,000 - $62,999 0.9226686 0.8991055
## 19 INCOME_F$63,000 + 0.8623762 0.8376588
## 20 U_R_FUrban 0.9653785 0.9455601
## 21 U_R_FRural 0.9885746 0.9415980
## 22 FACILITY_TYPE_FComprehensive Comm Ca Program 0.9546160 0.9290925
## 23 FACILITY_TYPE_FAcademic/Research Program 0.8716936 0.8484284
## 24 FACILITY_TYPE_FIntegrated Network Ca Program 0.9806766 0.9500188
## 25 FACILITY_LOCATION_FMiddle Atlantic 0.9960048 0.9637307
## 26 FACILITY_LOCATION_FSouth Atlantic 0.9725862 0.9420556
## 27 FACILITY_LOCATION_FEast North Central 1.0765733 1.0419151
## 28 FACILITY_LOCATION_FEast South Central 1.0640426 1.0238784
## 29 FACILITY_LOCATION_FWest North Central 1.0335592 0.9955606
## 30 FACILITY_LOCATION_FWest South Central 1.0153044 0.9747057
## 31 FACILITY_LOCATION_FMountain 1.0220666 0.9806641
## 32 FACILITY_LOCATION_FPacific 0.9476622 0.9153715
## 33 EDUCATION_F13 - 20.9% 0.9348816 0.9120022
## 34 EDUCATION_F7 - 12.9% 0.8888182 0.8658518
## 35 EDUCATION_FLess than 7% 0.7744613 0.7516428
## # ... with 2 more variables: conf.high <dbl>, p.value <dbl>
Predictors of Surgery
fit_surg <- glm(SURG_TF ~ AGE_F + SEX_F + RACE_F + INCOME_F + U_R_F +
FACILITY_TYPE_F + FACILITY_LOCATION_F + EDUCATION_F + EXPN_GROUP,
data = data %>% filter(SURGERY_YN != "Ukn") %>% droplevels() %>% mutate(SURGERY_YN = as.logical(SURGERY_YN)))
summary(fit_surg)
##
## Call:
## glm(formula = SURG_TF ~ AGE_F + SEX_F + RACE_F + INCOME_F + U_R_F +
## FACILITY_TYPE_F + FACILITY_LOCATION_F + EDUCATION_F + EXPN_GROUP,
## data = data %>% filter(SURGERY_YN != "Ukn") %>% droplevels() %>%
## mutate(SURGERY_YN = as.logical(SURGERY_YN)))
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.99423 0.03190 0.04440 0.05726 0.21648
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 0.9081399 0.0028620 317.304
## AGE_F(54,64] -0.0072041 0.0010786 -6.679
## AGE_F(64,74] -0.0081639 0.0010934 -7.466
## AGE_F(74,100] -0.0200655 0.0010744 -18.675
## SEX_FFemale 0.0109075 0.0007849 13.896
## RACE_FBlack -0.0929640 0.0049996 -18.594
## RACE_FOther/Unk -0.0006775 0.0030515 -0.222
## RACE_FAsian -0.0518461 0.0074247 -6.983
## INCOME_F$38,000 - $47,999 0.0041661 0.0015199 2.741
## INCOME_F$48,000 - $62,999 0.0085346 0.0015873 5.377
## INCOME_F$63,000 + 0.0110084 0.0017396 6.328
## U_R_FUrban 0.0050951 0.0012133 4.199
## U_R_FRural 0.0025631 0.0029320 0.874
## FACILITY_TYPE_FComprehensive Comm Ca Program 0.0246966 0.0016691 14.796
## FACILITY_TYPE_FAcademic/Research Program 0.0392540 0.0016438 23.880
## FACILITY_TYPE_FIntegrated Network Ca Program 0.0254413 0.0019155 13.282
## FACILITY_LOCATION_FMiddle Atlantic -0.0034108 0.0018257 -1.868
## FACILITY_LOCATION_FSouth Atlantic -0.0059582 0.0018019 -3.307
## FACILITY_LOCATION_FEast North Central -0.0053532 0.0018364 -2.915
## FACILITY_LOCATION_FEast South Central -0.0035544 0.0022293 -1.594
## FACILITY_LOCATION_FWest North Central -0.0093962 0.0020616 -4.558
## FACILITY_LOCATION_FWest South Central -0.0253217 0.0023654 -10.705
## FACILITY_LOCATION_FMountain -0.0120912 0.0023058 -5.244
## FACILITY_LOCATION_FPacific -0.0098457 0.0019394 -5.077
## EDUCATION_F13 - 20.9% 0.0067553 0.0015322 4.409
## EDUCATION_F7 - 12.9% 0.0114129 0.0015965 7.149
## EDUCATION_FLess than 7% 0.0162856 0.0017663 9.220
## EXPN_GROUPPre-Expansion 0.0086333 0.0011013 7.840
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## AGE_F(54,64] 2.41e-11 ***
## AGE_F(64,74] 8.27e-14 ***
## AGE_F(74,100] < 2e-16 ***
## SEX_FFemale < 2e-16 ***
## RACE_FBlack < 2e-16 ***
## RACE_FOther/Unk 0.824293
## RACE_FAsian 2.90e-12 ***
## INCOME_F$38,000 - $47,999 0.006124 **
## INCOME_F$48,000 - $62,999 7.59e-08 ***
## INCOME_F$63,000 + 2.49e-10 ***
## U_R_FUrban 2.68e-05 ***
## U_R_FRural 0.382028
## FACILITY_TYPE_FComprehensive Comm Ca Program < 2e-16 ***
## FACILITY_TYPE_FAcademic/Research Program < 2e-16 ***
## FACILITY_TYPE_FIntegrated Network Ca Program < 2e-16 ***
## FACILITY_LOCATION_FMiddle Atlantic 0.061737 .
## FACILITY_LOCATION_FSouth Atlantic 0.000944 ***
## FACILITY_LOCATION_FEast North Central 0.003556 **
## FACILITY_LOCATION_FEast South Central 0.110845
## FACILITY_LOCATION_FWest North Central 5.18e-06 ***
## FACILITY_LOCATION_FWest South Central < 2e-16 ***
## FACILITY_LOCATION_FMountain 1.57e-07 ***
## FACILITY_LOCATION_FPacific 3.84e-07 ***
## EDUCATION_F13 - 20.9% 1.04e-05 ***
## EDUCATION_F7 - 12.9% 8.78e-13 ***
## EDUCATION_FLess than 7% < 2e-16 ***
## EXPN_GROUPPre-Expansion 4.54e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 0.04499771)
##
## Null deviance: 14065 on 309989 degrees of freedom
## Residual deviance: 13948 on 309962 degrees of freedom
## (52236 observations deleted due to missingness)
## AIC: -81580
##
## Number of Fisher Scoring iterations: 2
exp(cbind("Odds ratio" = coef(fit_surg), confint.default(fit_surg, level = 0.95)))
## Odds ratio 2.5 %
## (Intercept) 2.4797057 2.4658347
## AGE_F(54,64] 0.9928218 0.9907252
## AGE_F(64,74] 0.9918693 0.9897459
## AGE_F(74,100] 0.9801345 0.9780726
## SEX_FFemale 1.0109672 1.0094131
## RACE_FBlack 0.9112263 0.9023407
## RACE_FOther/Unk 0.9993227 0.9933638
## RACE_FAsian 0.9494750 0.9357581
## INCOME_F$38,000 - $47,999 1.0041748 1.0011879
## INCOME_F$48,000 - $62,999 1.0085711 1.0054382
## INCOME_F$63,000 + 1.0110692 1.0076277
## U_R_FUrban 1.0051081 1.0027208
## U_R_FRural 1.0025663 0.9968215
## FACILITY_TYPE_FComprehensive Comm Ca Program 1.0250041 1.0216563
## FACILITY_TYPE_FAcademic/Research Program 1.0400346 1.0366892
## FACILITY_TYPE_FIntegrated Network Ca Program 1.0257677 1.0219238
## FACILITY_LOCATION_FMiddle Atlantic 0.9965950 0.9930353
## FACILITY_LOCATION_FSouth Atlantic 0.9940596 0.9905551
## FACILITY_LOCATION_FEast North Central 0.9946611 0.9910876
## FACILITY_LOCATION_FEast South Central 0.9964519 0.9921076
## FACILITY_LOCATION_FWest North Central 0.9906478 0.9866529
## FACILITY_LOCATION_FWest South Central 0.9749962 0.9704864
## FACILITY_LOCATION_FMountain 0.9879816 0.9835266
## FACILITY_LOCATION_FPacific 0.9902026 0.9864458
## EDUCATION_F13 - 20.9% 1.0067782 1.0037594
## EDUCATION_F7 - 12.9% 1.0114782 1.0083182
## EDUCATION_FLess than 7% 1.0164189 1.0129062
## EXPN_GROUPPre-Expansion 1.0086707 1.0064959
## 97.5 %
## (Intercept) 2.4936548
## AGE_F(54,64] 0.9949229
## AGE_F(64,74] 0.9939973
## AGE_F(74,100] 0.9822007
## SEX_FFemale 1.0125237
## RACE_FBlack 0.9201994
## RACE_FOther/Unk 1.0053174
## RACE_FAsian 0.9633928
## INCOME_F$38,000 - $47,999 1.0071707
## INCOME_F$48,000 - $62,999 1.0117137
## INCOME_F$63,000 + 1.0145225
## U_R_FUrban 1.0075010
## U_R_FRural 1.0083443
## FACILITY_TYPE_FComprehensive Comm Ca Program 1.0283628
## FACILITY_TYPE_FAcademic/Research Program 1.0433908
## FACILITY_TYPE_FIntegrated Network Ca Program 1.0296261
## FACILITY_LOCATION_FMiddle Atlantic 1.0001676
## FACILITY_LOCATION_FSouth Atlantic 0.9975764
## FACILITY_LOCATION_FEast North Central 0.9982476
## FACILITY_LOCATION_FEast South Central 1.0008152
## FACILITY_LOCATION_FWest North Central 0.9946588
## FACILITY_LOCATION_FWest South Central 0.9795270
## FACILITY_LOCATION_FMountain 0.9924568
## FACILITY_LOCATION_FPacific 0.9939737
## EDUCATION_F13 - 20.9% 1.0098061
## EDUCATION_F7 - 12.9% 1.0146482
## EDUCATION_FLess than 7% 1.0199438
## EXPN_GROUPPre-Expansion 1.0108502
Predictors of Metastasis at Time of Diagnosis, limit to those cases where data
about expansion status is available (> Age 39, non-ambiguous status states)
fit_mets <- glm(mets_at_dx_F ~ AGE_F + SEX_F + RACE_F + INCOME_F + U_R_F +
FACILITY_TYPE_F + FACILITY_LOCATION_F + EDUCATION_F + EXPN_GROUP,
data = no_Excludes)
summary(fit_mets)
##
## Call:
## glm(formula = mets_at_dx_F ~ AGE_F + SEX_F + RACE_F + INCOME_F +
## U_R_F + FACILITY_TYPE_F + FACILITY_LOCATION_F + EDUCATION_F +
## EXPN_GROUP, data = no_Excludes)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.08216 -0.02878 -0.02092 -0.01372 1.00266
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 0.0495593 0.0019342 25.623
## AGE_F(54,64] 0.0049569 0.0007282 6.807
## AGE_F(64,74] 0.0057453 0.0007388 7.777
## AGE_F(74,100] 0.0084310 0.0007270 11.598
## SEX_FFemale -0.0085557 0.0005312 -16.106
## RACE_FBlack 0.0223772 0.0033314 6.717
## RACE_FOther/Unk -0.0016802 0.0020669 -0.813
## RACE_FAsian 0.0237505 0.0050021 4.748
## INCOME_F$38,000 - $47,999 -0.0010712 0.0010236 -1.046
## INCOME_F$48,000 - $62,999 -0.0028864 0.0010698 -2.698
## INCOME_F$63,000 + -0.0063578 0.0011735 -5.418
## U_R_FUrban -0.0022755 0.0008187 -2.780
## U_R_FRural 0.0018322 0.0019826 0.924
## FACILITY_TYPE_FComprehensive Comm Ca Program -0.0064353 0.0011296 -5.697
## FACILITY_TYPE_FAcademic/Research Program -0.0098655 0.0011124 -8.869
## FACILITY_TYPE_FIntegrated Network Ca Program -0.0025561 0.0012934 -1.976
## FACILITY_LOCATION_FMiddle Atlantic 0.0017956 0.0012371 1.451
## FACILITY_LOCATION_FSouth Atlantic 0.0049151 0.0012196 4.030
## FACILITY_LOCATION_FEast North Central 0.0045108 0.0012441 3.626
## FACILITY_LOCATION_FEast South Central 0.0053204 0.0015035 3.539
## FACILITY_LOCATION_FWest North Central 0.0015550 0.0013967 1.113
## FACILITY_LOCATION_FWest South Central 0.0146708 0.0015962 9.191
## FACILITY_LOCATION_FMountain 0.0084461 0.0015581 5.421
## FACILITY_LOCATION_FPacific -0.0015244 0.0013144 -1.160
## EDUCATION_F13 - 20.9% -0.0004141 0.0010313 -0.402
## EDUCATION_F7 - 12.9% -0.0032919 0.0010757 -3.060
## EDUCATION_FLess than 7% -0.0051212 0.0011914 -4.299
## EXPN_GROUPPre-Expansion -0.0224662 0.0007473 -30.063
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## AGE_F(54,64] 1.00e-11 ***
## AGE_F(64,74] 7.48e-15 ***
## AGE_F(74,100] < 2e-16 ***
## SEX_FFemale < 2e-16 ***
## RACE_FBlack 1.86e-11 ***
## RACE_FOther/Unk 0.416276
## RACE_FAsian 2.05e-06 ***
## INCOME_F$38,000 - $47,999 0.295348
## INCOME_F$48,000 - $62,999 0.006975 **
## INCOME_F$63,000 + 6.04e-08 ***
## U_R_FUrban 0.005444 **
## U_R_FRural 0.355399
## FACILITY_TYPE_FComprehensive Comm Ca Program 1.22e-08 ***
## FACILITY_TYPE_FAcademic/Research Program < 2e-16 ***
## FACILITY_TYPE_FIntegrated Network Ca Program 0.048125 *
## FACILITY_LOCATION_FMiddle Atlantic 0.146646
## FACILITY_LOCATION_FSouth Atlantic 5.58e-05 ***
## FACILITY_LOCATION_FEast North Central 0.000288 ***
## FACILITY_LOCATION_FEast South Central 0.000402 ***
## FACILITY_LOCATION_FWest North Central 0.265582
## FACILITY_LOCATION_FWest South Central < 2e-16 ***
## FACILITY_LOCATION_FMountain 5.94e-08 ***
## FACILITY_LOCATION_FPacific 0.246137
## EDUCATION_F13 - 20.9% 0.688029
## EDUCATION_F7 - 12.9% 0.002212 **
## EDUCATION_FLess than 7% 1.72e-05 ***
## EXPN_GROUPPre-Expansion < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 0.02156817)
##
## Null deviance: 7052.0 on 325127 degrees of freedom
## Residual deviance: 7011.8 on 325100 degrees of freedom
## (10945 observations deleted due to missingness)
## AIC: -324662
##
## Number of Fisher Scoring iterations: 2
exp(cbind("Odds ratio" = coef(fit_mets), confint.default(fit_surg, level = 0.95)))
## Odds ratio 2.5 %
## (Intercept) 1.0508079 2.4658347
## AGE_F(54,64] 1.0049692 0.9907252
## AGE_F(64,74] 1.0057619 0.9897459
## AGE_F(74,100] 1.0084667 0.9780726
## SEX_FFemale 0.9914808 1.0094131
## RACE_FBlack 1.0226295 0.9023407
## RACE_FOther/Unk 0.9983212 0.9933638
## RACE_FAsian 1.0240347 0.9357581
## INCOME_F$38,000 - $47,999 0.9989294 1.0011879
## INCOME_F$48,000 - $62,999 0.9971178 1.0054382
## INCOME_F$63,000 + 0.9936624 1.0076277
## U_R_FUrban 0.9977271 1.0027208
## U_R_FRural 1.0018339 0.9968215
## FACILITY_TYPE_FComprehensive Comm Ca Program 0.9935853 1.0216563
## FACILITY_TYPE_FAcademic/Research Program 0.9901830 1.0366892
## FACILITY_TYPE_FIntegrated Network Ca Program 0.9974472 1.0219238
## FACILITY_LOCATION_FMiddle Atlantic 1.0017972 0.9930353
## FACILITY_LOCATION_FSouth Atlantic 1.0049272 0.9905551
## FACILITY_LOCATION_FEast North Central 1.0045209 0.9910876
## FACILITY_LOCATION_FEast South Central 1.0053346 0.9921076
## FACILITY_LOCATION_FWest North Central 1.0015562 0.9866529
## FACILITY_LOCATION_FWest South Central 1.0147790 0.9704864
## FACILITY_LOCATION_FMountain 1.0084818 0.9835266
## FACILITY_LOCATION_FPacific 0.9984767 0.9864458
## EDUCATION_F13 - 20.9% 0.9995860 1.0037594
## EDUCATION_F7 - 12.9% 0.9967135 1.0083182
## EDUCATION_FLess than 7% 0.9948919 1.0129062
## EXPN_GROUPPre-Expansion 0.9777843 1.0064959
## 97.5 %
## (Intercept) 2.4936548
## AGE_F(54,64] 0.9949229
## AGE_F(64,74] 0.9939973
## AGE_F(74,100] 0.9822007
## SEX_FFemale 1.0125237
## RACE_FBlack 0.9201994
## RACE_FOther/Unk 1.0053174
## RACE_FAsian 0.9633928
## INCOME_F$38,000 - $47,999 1.0071707
## INCOME_F$48,000 - $62,999 1.0117137
## INCOME_F$63,000 + 1.0145225
## U_R_FUrban 1.0075010
## U_R_FRural 1.0083443
## FACILITY_TYPE_FComprehensive Comm Ca Program 1.0283628
## FACILITY_TYPE_FAcademic/Research Program 1.0433908
## FACILITY_TYPE_FIntegrated Network Ca Program 1.0296261
## FACILITY_LOCATION_FMiddle Atlantic 1.0001676
## FACILITY_LOCATION_FSouth Atlantic 0.9975764
## FACILITY_LOCATION_FEast North Central 0.9982476
## FACILITY_LOCATION_FEast South Central 1.0008152
## FACILITY_LOCATION_FWest North Central 0.9946588
## FACILITY_LOCATION_FWest South Central 0.9795270
## FACILITY_LOCATION_FMountain 0.9924568
## FACILITY_LOCATION_FPacific 0.9939737
## EDUCATION_F13 - 20.9% 1.0098061
## EDUCATION_F7 - 12.9% 1.0146482
## EDUCATION_FLess than 7% 1.0199438
## EXPN_GROUPPre-Expansion 1.0108502
